{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/path-length-regularization","slug":"path-length-regularization","name":"Path Length Regularization","full_name":"Path Length Regularization","full_name_withheld":false,"description_markdown":"**Path Length Regularization** is a type of regularization for [generative adversarial networks](https://paperswithcode.com/methods/category/generative-adversarial-networks) that encourages good conditioning in the mapping from latent codes to images. The idea is to encourage that a fixed-size step in the latent space $\\mathcal{W}$ results in a non-zero, fixed-magnitude change in the image.\r\n\r\nWe can measure the deviation from this ideal empirically by stepping into random directions in the image space and observing the corresponding $\\mathbf{w}$ gradients. These gradients should have close to an equal length regardless of $\\mathbf{w}$ or the image-space direction, indicating that the mapping from the latent space to image space is well-conditioned.\r\n\r\nAt a single $\\mathbf{w} \\in \\mathcal{W}$ the local metric scaling properties of the generator mapping $g\\left(\\mathbf{w}\\right) : \\mathcal{W} \\rightarrow \\mathcal{Y}$ are captured by the Jacobian matrix $\\mathbf{J\\_{w}} = \\delta{g}\\left(\\mathbf{w}\\right)/\\delta{\\mathbf{w}}$. Motivated by the desire to preserve the expected lengths of vectors regardless of the direction, we formulate the regularizer as:\r\n\r\n$$ \\mathbb{E}\\_{\\mathbf{w},\\mathbf{y} \\sim \\mathcal{N}\\left(0, \\mathbf{I}\\right)} \\left(||\\mathbf{J}^{\\mathbf{T}}\\_{\\mathbf{w}}\\mathbf{y}||\\_{2} - a\\right)^{2} $$\r\n\r\nwhere $y$ are random images with normally distributed pixel intensities, and $w \\sim f\\left(z\\right)$, where $z$ are normally distributed. \r\n\r\nTo avoid explicit computation of the Jacobian matrix, we use the identity $\\mathbf{J}^{\\mathbf{T}}\\_{\\mathbf{w}}\\mathbf{y} = \\nabla\\_{\\mathbf{w}}\\left(g\\left(\\mathbf{w}\\right)·y\\right)$, which is efficiently computable using standard backpropagation. The constant $a$ is set dynamically during optimization as the long-running exponential moving average of the lengths $||\\mathbf{J}^{\\mathbf{T}}\\_{\\mathbf{w}}\\mathbf{y}||\\_{2}$, allowing the optimization to find a suitable global scale by itself.\r\n\r\nThe authors note that they find that path length regularization leads to more reliable and consistently behaving models, making architecture exploration easier. They also observe that the smoother generator is significantly easier to invert.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/1912.04958v2","title":"Analyzing and Improving the Image Quality of StyleGAN","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/NVlabs/stylegan2/blob/7d3145d23013607b987db30736f89fb1d3e10fad/training/loss.py#L156","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Regularization","url":"/methods/category/regularization","pwc_aliases":[]}],"n_papers_tagged":182,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"pose-and-facial-expression-transfer-by-using","title":"Pose and Facial Expression Transfer by using StyleGAN","date":"2025-04-17","arxiv_id":"2504.13021","n_code_links":0,"syntology":null},{"paper":"/paper/the-gan-is-dead-long-live-the-gan-a-modern","slug":"the-gan-is-dead-long-live-the-gan-a-modern","title":"The GAN is dead; long live the GAN! A Modern GAN Baseline","date":"2025-01-09","arxiv_id":"2501.05441","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":7,"n_instrument":2,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["brownvc/r3gan"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/singular-value-scaling-efficient-generative","slug":"singular-value-scaling-efficient-generative","title":"Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement","date":"2024-12-23","arxiv_id":"2412.17387","n_code_links":1,"syntology":null},{"paper":null,"slug":"mytimemachine-personalized-facial-age","title":"MyTimeMachine: Personalized Facial Age Transformation","date":"2024-11-21","arxiv_id":"2411.14521","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-panoptic-interpretation-of","slug":"unsupervised-panoptic-interpretation-of","title":"Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization","date":"2024-10-27","arxiv_id":"2410.20573","n_code_links":1,"syntology":null},{"paper":null,"slug":"stool-recognition-for-colorectal-cancer","title":"Stool Recognition for Colorectal Cancer Detection through Deep Learning","date":"2024-10-19","arxiv_id":"2410.17288","n_code_links":0,"syntology":null},{"paper":"/paper/mm2latent-text-to-facial-image-generation-and","slug":"mm2latent-text-to-facial-image-generation-and","title":"MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance","date":"2024-09-17","arxiv_id":"2409.11010","n_code_links":1,"syntology":null},{"paper":null,"slug":"bridging-the-gap-studio-like-avatar-creation","title":"Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture","date":"2024-07-28","arxiv_id":"2407.19593","n_code_links":0,"syntology":null},{"paper":"/paper/face-reconstruction-transfer-attack-as-out-of","slug":"face-reconstruction-transfer-attack-as-out-of","title":"Face Reconstruction Transfer Attack as Out-of-Distribution Generalization","date":"2024-07-02","arxiv_id":"2407.02403","n_code_links":1,"syntology":null},{"paper":null,"slug":"controlling-face-s-frame-generation-in","title":"Controlling Face's Frame generation in StyleGAN's latent space operations: Modifying faces to deceive our memory","date":"2024-06-30","arxiv_id":"2407.00803","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-the-feature-extractor-networks-for","slug":"analyzing-the-feature-extractor-networks-for","title":"Analyzing the Feature Extractor Networks for Face Image Synthesis","date":"2024-06-04","arxiv_id":"2406.02153","n_code_links":1,"syntology":null},{"paper":null,"slug":"nickel-and-diming-your-gan-a-dual-method","title":"Nickel and Diming Your GAN: A Dual-Method Approach to Enhancing GAN Efficiency via Knowledge Distillation","date":"2024-05-19","arxiv_id":"2405.11614","n_code_links":0,"syntology":null},{"paper":null,"slug":"sampling-strategies-for-mitigating-bias-in","title":"Sampling Strategies for Mitigating Bias in Face Synthesis Methods","date":"2024-05-18","arxiv_id":"2405.11320","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-print-and-scan-in-heterogeneous","title":"The Impact of Print-Scanning in Heterogeneous Morph Evaluation Scenarios","date":"2024-04-09","arxiv_id":"2404.06559","n_code_links":0,"syntology":null},{"paper":"/paper/latentswap-an-efficient-latent-code-mapping","slug":"latentswap-an-efficient-latent-code-mapping","title":"LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping","date":"2024-02-28","arxiv_id":"2402.18351","n_code_links":1,"syntology":null},{"paper":null,"slug":"geometry-aware-3d-generation-from-in-the-wild","title":"Geometry aware 3D generation from in-the-wild images in ImageNet","date":"2024-01-31","arxiv_id":"2402.00225","n_code_links":0,"syntology":null},{"paper":null,"slug":"unihda-towards-universal-hybrid-domain","title":"UniHDA: A Unified and Versatile Framework for Multi-Modal Hybrid Domain Adaptation","date":"2024-01-23","arxiv_id":"2401.12596","n_code_links":0,"syntology":null},{"paper":"/paper/huref-human-readable-fingerprint-for-large","slug":"huref-human-readable-fingerprint-for-large","title":"HuRef: HUman-REadable Fingerprint for Large Language Models","date":"2023-12-08","arxiv_id":"2312.04828","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lumia-group/huref"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"synthetic-speaking-children-why-we-need-them","title":"Synthetic Speaking Children -- Why We Need Them and How to Make Them","date":"2023-11-08","arxiv_id":"2311.06307","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-measuring-fairness-in-generative-models","title":"On Measuring Fairness in Generative Models","date":"2023-10-30","arxiv_id":"2310.19297","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-the-authenticity-of-rendered","title":"Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning","date":"2023-10-06","arxiv_id":"2310.04194","n_code_links":0,"syntology":null},{"paper":"/paper/fg-net-facial-action-unit-detection-with","slug":"fg-net-facial-action-unit-detection-with","title":"FG-Net: Facial Action Unit Detection with Generalizable Pyramidal Features","date":"2023-08-23","arxiv_id":"2308.12380","n_code_links":1,"syntology":null},{"paper":null,"slug":"fair-gans-through-model-rebalancing-with","title":"Fair GANs through model rebalancing for extremely imbalanced class distributions","date":"2023-08-16","arxiv_id":"2308.08638","n_code_links":0,"syntology":null},{"paper":null,"slug":"childgan-large-scale-synthetic-child-facial","title":"ChildGAN: Large Scale Synthetic Child Facial Data Using Domain Adaptation in StyleGAN","date":"2023-07-25","arxiv_id":"2307.13746","n_code_links":0,"syntology":null},{"paper":"/paper/hyperreenact-one-shot-reenactment-via-jointly","slug":"hyperreenact-one-shot-reenactment-via-jointly","title":"HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces","date":"2023-07-20","arxiv_id":"2307.10797","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["stelabou/hyperreenact"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"stylegan3-generative-networks-for-improving","title":"StyleGAN3: Generative Networks for Improving the Equivariance of Translation and Rotation","date":"2023-07-08","arxiv_id":"2307.03898","n_code_links":0,"syntology":null},{"paper":"/paper/seeing-is-not-believing-an-identity-hider-for","slug":"seeing-is-not-believing-an-identity-hider-for","title":"Seeing is not Believing: An Identity Hider for Human Vision Privacy Protection","date":"2023-07-02","arxiv_id":"2307.00481","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-for-cancer-prognosis-prediction","title":"Deep Learning for Cancer Prognosis Prediction Using Portrait Photos by StyleGAN Embedding","date":"2023-06-26","arxiv_id":"2306.14596","n_code_links":0,"syntology":null},{"paper":null,"slug":"fd-on-understanding-the-role-of-deep-feature","title":"F?D: On understanding the role of deep feature spaces on face generation evaluation","date":"2023-05-31","arxiv_id":"2305.20048","n_code_links":0,"syntology":null},{"paper":null,"slug":"bright-bi-level-feature-representation-of","title":"BRICS: Bi-level feature Representation of Image CollectionS","date":"2023-05-29","arxiv_id":"2305.18601","n_code_links":0,"syntology":null},{"paper":"/paper/spider-gan-leveraging-friendly-neighbors-to","slug":"spider-gan-leveraging-friendly-neighbors-to","title":"Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Training","date":"2023-05-12","arxiv_id":"2305.07613","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["darthsid95/clean-sid","darthsid95/spiderstylegan"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/zero-shot-racially-balanced-dataset","slug":"zero-shot-racially-balanced-dataset","title":"Zero-shot racially balanced dataset generation using an existing biased StyleGAN2","date":"2023-05-12","arxiv_id":"2305.07710","n_code_links":1,"syntology":null},{"paper":"/paper/improving-synthetically-generated-image","slug":"improving-synthetically-generated-image","title":"Improving Synthetically Generated Image Detection in Cross-Concept Settings","date":"2023-04-24","arxiv_id":"2304.12053","n_code_links":1,"syntology":null},{"paper":"/paper/pg-vton-a-novel-image-based-virtual-try-on","slug":"pg-vton-a-novel-image-based-virtual-try-on","title":"PG-VTON: A Novel Image-Based Virtual Try-On Method via Progressive Inference Paradigm","date":"2023-04-18","arxiv_id":"2304.08956","n_code_links":1,"syntology":null},{"paper":"/paper/attributing-image-generative-models-using","slug":"attributing-image-generative-models-using","title":"Attributing Image Generative Models using Latent Fingerprints","date":"2023-04-17","arxiv_id":"2304.09752","n_code_links":1,"syntology":null},{"paper":null,"slug":"id2image-leakage-of-non-id-information-into","title":"ID2image: Leakage of non-ID information into face descriptors and inversion from descriptors to images","date":"2023-04-15","arxiv_id":"2304.07522","n_code_links":0,"syntology":null},{"paper":"/paper/patmat-person-aware-tuning-of-mask-aware","slug":"patmat-person-aware-tuning-of-mask-aware","title":"PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face Inpainting","date":"2023-04-12","arxiv_id":"2304.06107","n_code_links":2,"syntology":null},{"paper":null,"slug":"deepfake-detection-of-occluded-images-using-a","title":"Deepfake Detection of Occluded Images Using a Patch-based Approach","date":"2023-04-10","arxiv_id":"2304.04537","n_code_links":0,"syntology":null},{"paper":"/paper/prefgen-preference-guided-image-generation","slug":"prefgen-preference-guided-image-generation","title":"PrefGen: Preference Guided Image Generation with Relative Attributes","date":"2023-04-01","arxiv_id":"2304.00185","n_code_links":1,"syntology":null},{"paper":null,"slug":"sequential-training-of-gans-against-gan","title":"Sequential training of GANs against GAN-classifiers reveals correlated \"knowledge gaps\" present among independently trained GAN instances","date":"2023-03-27","arxiv_id":"2303.15533","n_code_links":0,"syntology":null},{"paper":null,"slug":"spatial-latent-representations-in-generative","title":"Spatial Latent Representations in Generative Adversarial Networks for Image Generation","date":"2023-03-25","arxiv_id":"2303.14552","n_code_links":0,"syntology":null},{"paper":null,"slug":"wasserstein-loss-for-semantic-editing-in-the","title":"Wasserstein Loss for Semantic Editing in the Latent Space of GANs","date":"2023-03-22","arxiv_id":"2304.10508","n_code_links":0,"syntology":null},{"paper":null,"slug":"coralstyleclip-co-optimized-region-and-layer","title":"CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editing","date":"2023-03-09","arxiv_id":"2303.05031","n_code_links":0,"syntology":null},{"paper":"/paper/riddle-reversible-and-diversified-de","slug":"riddle-reversible-and-diversified-de","title":"RiDDLE: Reversible and Diversified De-identification with Latent Encryptor","date":"2023-03-09","arxiv_id":"2303.05171","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-face-swapping-via-adaptive-latent","title":"End-to-end Face-swapping via Adaptive Latent Representation Learning","date":"2023-03-07","arxiv_id":"2303.04186","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-defect-image-generation-via-defect","slug":"few-shot-defect-image-generation-via-defect","title":"Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation","date":"2023-03-04","arxiv_id":"2303.02389","n_code_links":1,"syntology":null},{"paper":"/paper/gradient-adjusting-networks-for-domain","slug":"gradient-adjusting-networks-for-domain","title":"Gradient Adjusting Networks for Domain Inversion","date":"2023-02-22","arxiv_id":"2302.11413","n_code_links":1,"syntology":null},{"paper":null,"slug":"one-shot-face-video-re-enactment-using-hybrid","title":"One-Shot Face Video Re-enactment using Hybrid Latent Spaces of StyleGAN2","date":"2023-02-15","arxiv_id":"2302.07848","n_code_links":0,"syntology":null},{"paper":null,"slug":"conceptual-and-hierarchical-latent-space","title":"Conceptual and Hierarchical Latent Space Decomposition for Face Editing","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-one-shot-face-video-re-enactment-using","title":"Robust One-Shot Face Video Re-enactment using Hybrid Latent Spaces of StyleGAN2","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/stylegene-crossover-and-mutation-of-region","slug":"stylegene-crossover-and-mutation-of-region","title":"StyleGene: Crossover and Mutation of Region-Level Facial Genes for Kinship Face Synthesis","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"album-cover-art-image-generation-with","title":"Album cover art image generation with Generative Adversarial Networks","date":"2022-12-09","arxiv_id":"2212.04844","n_code_links":0,"syntology":null},{"paper":"/paper/glead-improving-gans-with-a-generator-leading","slug":"glead-improving-gans-with-a-generator-leading","title":"GLeaD: Improving GANs with A Generator-Leading Task","date":"2022-12-07","arxiv_id":"2212.03752","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ezioby/glead"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/brain-tumor-synthetic-data-generation-with","slug":"brain-tumor-synthetic-data-generation-with","title":"Brain Tumor Synthetic Data Generation with Adaptive StyleGANs","date":"2022-12-04","arxiv_id":"2212.01772","n_code_links":1,"syntology":null},{"paper":"/paper/dense-interspecies-face-embedding","slug":"dense-interspecies-face-embedding","title":"Dense Interspecies Face Embedding","date":"2022-11-28","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-2d-and-3d-master-faces-for","title":"Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution","date":"2022-11-25","arxiv_id":"2211.13964","n_code_links":0,"syntology":null},{"paper":"/paper/ilsgan-independent-layer-synthesis-for","slug":"ilsgan-independent-layer-synthesis-for","title":"ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentation","date":"2022-11-25","arxiv_id":"2211.13974","n_code_links":1,"syntology":null},{"paper":null,"slug":"unsupervised-anomaly-appraisal-of-cleft-faces","title":"Unsupervised Anomaly Appraisal of Cleft Faces Using a StyleGAN2-based Model Adaptation Technique","date":"2022-11-12","arxiv_id":"2211.06659","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-adversarial-active-sampling-based-data","title":"An Adversarial Active Sampling-based Data Augmentation Framework for Manufacturable Chip Design","date":"2022-10-27","arxiv_id":"2210.15765","n_code_links":0,"syntology":null},{"paper":null,"slug":"atlas-flow-compatible-local-structures-on-the","title":"Atlas flow : compatible local structures on the manifold","date":"2022-10-24","arxiv_id":"2210.14149","n_code_links":0,"syntology":null},{"paper":null,"slug":"if-gan-a-novel-generator-architecture-with","title":"Improving GANs with a Feature Cycling Generator","date":"2022-10-18","arxiv_id":"2210.09638","n_code_links":0,"syntology":null},{"paper":"/paper/intra-source-style-augmentation-for-improved","slug":"intra-source-style-augmentation-for-improved","title":"Intra-Source Style Augmentation for Improved Domain Generalization","date":"2022-10-18","arxiv_id":"2210.10175","n_code_links":1,"syntology":null},{"paper":null,"slug":"landmark-enforcement-and-style-manipulation","title":"Landmark Enforcement and Style Manipulation for Generative Morphing","date":"2022-10-18","arxiv_id":"2210.10182","n_code_links":0,"syntology":null},{"paper":"/paper/hyperdomainnet-universal-domain-adaptation","slug":"hyperdomainnet-universal-domain-adaptation","title":"HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks","date":"2022-10-17","arxiv_id":"2210.08884","n_code_links":1,"syntology":{"ran":8,"of":16,"n_ran_checked":6,"n_instrument":2,"unverified":8,"pointer_only":0,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","official":{"repos":["macderru/hyperdomainnet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multistylegan-multiple-one-shot-face","title":"MultiStyleGAN: Multiple One-shot Image Stylizations using a Single GAN","date":"2022-10-08","arxiv_id":"2210.04120","n_code_links":0,"syntology":null},{"paper":"/paper/stylemask-disentangling-the-style-space-of","slug":"stylemask-disentangling-the-style-space-of","title":"StyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment","date":"2022-09-27","arxiv_id":"2209.13375","n_code_links":1,"syntology":null},{"paper":null,"slug":"styleswap-style-based-generator-empowers","title":"StyleSwap: Style-Based Generator Empowers Robust Face Swapping","date":"2022-09-27","arxiv_id":"2209.13514","n_code_links":0,"syntology":null},{"paper":"/paper/generative-visual-prompt-unifying","slug":"generative-visual-prompt-unifying","title":"Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models","date":"2022-09-14","arxiv_id":"2209.06970","n_code_links":1,"syntology":null},{"paper":"/paper/deep-generative-modeling-on-limited-data-with","slug":"deep-generative-modeling-on-limited-data-with","title":"Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models","date":"2022-08-30","arxiv_id":"2208.14133","n_code_links":1,"syntology":null},{"paper":"/paper/mind-the-gap-in-distilling-stylegans","slug":"mind-the-gap-in-distilling-stylegans","title":"Mind the Gap in Distilling StyleGANs","date":"2022-08-18","arxiv_id":"2208.08840","n_code_links":1,"syntology":null},{"paper":"/paper/style-your-hair-latent-optimization-for-pose","slug":"style-your-hair-latent-optimization-for-pose","title":"Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment","date":"2022-08-16","arxiv_id":"2208.07765","n_code_links":1,"syntology":null},{"paper":"/paper/language-guided-face-animation-by-recurrent","slug":"language-guided-face-animation-by-recurrent","title":"Language-Guided Face Animation by Recurrent StyleGAN-based Generator","date":"2022-08-11","arxiv_id":"2208.05617","n_code_links":1,"syntology":null},{"paper":null,"slug":"hypernst-hyper-networks-for-neural-style","title":"HyperNST: Hyper-Networks for Neural Style Transfer","date":"2022-08-09","arxiv_id":"2208.04807","n_code_links":0,"syntology":null},{"paper":"/paper/design-what-you-desire-icon-generation-from","slug":"design-what-you-desire-icon-generation-from","title":"Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels","date":"2022-07-31","arxiv_id":"2208.00439","n_code_links":1,"syntology":null},{"paper":null,"slug":"paired-cross-modal-data-augmentation-for-fine","title":"Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval","date":"2022-07-29","arxiv_id":"2207.14428","n_code_links":0,"syntology":null},{"paper":"/paper/generating-diverse-vocal-bursts-with","slug":"generating-diverse-vocal-bursts-with","title":"Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms","date":"2022-06-25","arxiv_id":"2206.12563","n_code_links":1,"syntology":null},{"paper":"/paper/sdf-stylegan-implicit-sdf-based-stylegan-for","slug":"sdf-stylegan-implicit-sdf-based-stylegan-for","title":"SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation","date":"2022-06-24","arxiv_id":"2206.12055","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhengxinyang/sdf-stylegan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/studiogan-a-taxonomy-and-benchmark-of-gans","slug":"studiogan-a-taxonomy-and-benchmark-of-gans","title":"StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis","date":"2022-06-19","arxiv_id":"2206.09479","n_code_links":2,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["POSTECH-CVLab/PyTorch-StudioGAN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/spatially-adaptive-multilayer-selection-for-1","slug":"spatially-adaptive-multilayer-selection-for-1","title":"Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing","date":"2022-06-16","arxiv_id":"2206.08357","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["adobe-research/sam_inversion"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"enhancing-quality-of-pose-varied-face","title":"Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior","date":"2022-05-28","arxiv_id":"2205.14377","n_code_links":0,"syntology":null},{"paper":null,"slug":"looks-like-magic-transfer-learning-in-gans-to","title":"Looks Like Magic: Transfer Learning in GANs to Generate New Card Illustrations","date":"2022-05-28","arxiv_id":"2205.14442","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-to-face-generation-with-stylegan2","title":"Text-to-Face Generation with StyleGAN2","date":"2022-05-25","arxiv_id":"2205.12512","n_code_links":0,"syntology":null},{"paper":"/paper/are-gan-based-morphs-threatening-face","slug":"are-gan-based-morphs-threatening-face","title":"Are GAN-based Morphs Threatening Face Recognition?","date":"2022-05-05","arxiv_id":"2205.02496","n_code_links":1,"syntology":null},{"paper":null,"slug":"blobgan-spatially-disentangled-scene","title":"BlobGAN: Spatially Disentangled Scene Representations","date":"2022-05-05","arxiv_id":"2205.02837","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-adversarial-network-based-3","title":"Generative Adversarial Network Based Synthetic Learning and a Novel Domain Relevant Loss Term for Spine Radiographs","date":"2022-05-05","arxiv_id":"2205.02843","n_code_links":0,"syntology":null},{"paper":"/paper/bioculargan-bimodal-synthesis-and-annotation","slug":"bioculargan-bimodal-synthesis-and-annotation","title":"BiOcularGAN: Bimodal Synthesis and Annotation of Ocular Images","date":"2022-05-03","arxiv_id":"2205.01536","n_code_links":1,"syntology":null},{"paper":null,"slug":"evolutionary-latent-space-search-for-driving","title":"Evolutionary latent space search for driving human portrait generation","date":"2022-04-25","arxiv_id":"2204.11887","n_code_links":0,"syntology":null},{"paper":"/paper/stylet2f-generating-human-faces-from-textual","slug":"stylet2f-generating-human-faces-from-textual","title":"StyleT2F: Generating Human Faces from Textual Description Using StyleGAN2","date":"2022-04-17","arxiv_id":"2204.07924","n_code_links":1,"syntology":null},{"paper":null,"slug":"petrogan-a-novel-gan-based-approach-to","title":"PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasets","date":"2022-04-07","arxiv_id":"2204.05114","n_code_links":0,"syntology":null},{"paper":null,"slug":"thermal-to-visible-image-synthesis-under","title":"Thermal to Visible Image Synthesis under Atmospheric Turbulence","date":"2022-04-06","arxiv_id":"2204.03057","n_code_links":0,"syntology":null},{"paper":"/paper/pixelfolder-an-efficient-progressive-pixel","slug":"pixelfolder-an-efficient-progressive-pixel","title":"PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation","date":"2022-04-02","arxiv_id":"2204.00833","n_code_links":1,"syntology":null},{"paper":"/paper/encode-in-style-latent-based-video-encoding","slug":"encode-in-style-latent-based-video-encoding","title":"Expressive Talking Head Video Encoding in StyleGAN2 Latent-Space","date":"2022-03-28","arxiv_id":"2203.14512","n_code_links":2,"syntology":null},{"paper":"/paper/which-generative-adversarial-network-yields","slug":"which-generative-adversarial-network-yields","title":"Robust deep learning for eye fundus images: Bridging real and synthetic data for enhancing generalization","date":"2022-03-25","arxiv_id":"2203.13856","n_code_links":2,"syntology":null},{"paper":"/paper/a-naive-method-to-discover-directions-in-the","slug":"a-naive-method-to-discover-directions-in-the","title":"A naive method to discover directions in the StyleGAN2 latent space","date":"2022-03-19","arxiv_id":"2203.10373","n_code_links":1,"syntology":null},{"paper":null,"slug":"fantastic-style-channels-and-where-to-find","title":"Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANs","date":"2022-03-16","arxiv_id":"2203.08516","n_code_links":0,"syntology":null},{"paper":"/paper/the-role-of-imagenet-classes-in-frechet","slug":"the-role-of-imagenet-classes-in-frechet","title":"The Role of ImageNet Classes in Fréchet Inception Distance","date":"2022-03-11","arxiv_id":"2203.06026","n_code_links":2,"syntology":null},{"paper":null,"slug":"region-aware-face-swapping","title":"Region-Aware Face Swapping","date":"2022-03-09","arxiv_id":"2203.04564","n_code_links":0,"syntology":null},{"paper":"/paper/polarity-sampling-quality-and-diversity","slug":"polarity-sampling-quality-and-diversity","title":"Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values","date":"2022-03-03","arxiv_id":"2203.01993","n_code_links":1,"syntology":null},{"paper":"/paper/when-do-gans-replicate-on-the-choice-of-1","slug":"when-do-gans-replicate-on-the-choice-of-1","title":"When do GANs replicate? On the choice of dataset size","date":"2022-02-23","arxiv_id":"2202.11765","n_code_links":1,"syntology":null},{"paper":null,"slug":"fairstyle-debiasing-stylegan2-with-style","title":"FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations","date":"2022-02-13","arxiv_id":"2202.06240","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":182,"with_a_code_link":109,"where_syntology_ran_a_sample":34,"not_listed_spam_title":0,"listed":182,"listed_where_code_ran":34,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":28,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":28,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":34,"papers_where_code_ran_first_page":"/method/path-length-regularization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":2,"url":"/method/path-length-regularization/papers/2","json":"/method/path-length-regularization/papers/2.json","rows":82},{"order":"ran","page":1,"of":1,"url":"/method/path-length-regularization/papers/ran/1","json":"/method/path-length-regularization/papers/ran/1.json","rows":34}],"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":53},{"task":"/task/attribute","name":"Attribute","papers":20},{"task":null,"name":"Generative Adversarial Network","papers":20},{"task":"/task/image-manipulation","name":"Image Manipulation","papers":14},{"task":"/task/disentanglement","name":"Disentanglement","papers":13},{"task":"/task/face-generation","name":"Face Generation","papers":13},{"task":"/task/diversity","name":"Diversity","papers":11},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":10},{"task":"/task/face-recognition","name":"Face Recognition","papers":10},{"task":"/task/conditional-image-generation","name":"Conditional Image Generation","papers":7},{"task":"/task/translation","name":"Translation","papers":7},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":6},{"task":"/task/face-swapping","name":"Face Swapping","papers":6},{"task":"/task/image-to-image-translation","name":"Image-to-Image Translation","papers":5},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":5},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":5},{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":4},{"task":"/task/segmentation","name":"Segmentation","papers":4},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":4},{"task":"/task/style-transfer","name":"Style Transfer","papers":4}],"tasks_shown":20,"n_tasks":139,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":22},{"year":"2021","papers":52},{"year":"2022","papers":56},{"year":"2023","papers":34},{"year":"2024","papers":15},{"year":"2025","papers":2}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/path-length-regularization"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Path%20Length%20Regularization","read_at":"2026-10-05T01:00:05+00:00","query":"Path Length Regularization","kind":"method","have":"unverified_code","tier":null,"verified_implementation":false,"level":1,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"Path Regularization","origin_arxiv_id":"2110.09548"},"resolution":"token_match","resolved_name_differs":true,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"unknown","archive_paper_arxiv_id":null,"repositories":{"listed":null,"in_graph":0,"list_truncated":null,"strongest_link":null},"retrieve_with":"get_reference_implementation(name='Path Regularization', min_level=1)","name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2110.09548","citations":22},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'Path Length Regularization'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2110.09548","page":null,"syntology_url":"https://syntology.ai/paper/2110.09548","in_graph_layer":false,"samples":0},"line":"for a different name, 'Path Regularization': source stored, below machine verification, at level V1 (unverified_code): present, not executed on a fixture. The lookup matched a different name in Syntology's graph, 'Path Regularization' (resolution: token_match); this answer is about that name. The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2110.09548) is about this method is not checked.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"a460c71cda16eb98b9dd5a4e4e8cefebded4733039feceb0195d06eb9b58d835","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}