{"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/vgg-loss","slug":"vgg-loss","name":"VGG Loss","full_name":"VGG Loss","full_name_withheld":false,"description_markdown":"**VGG Loss** is a type of content loss introduced in the [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://paperswithcode.com/paper/perceptual-losses-for-real-time-style) super-resolution and style transfer framework. It is an alternative to pixel-wise losses; VGG Loss attempts to be closer to perceptual similarity. The [VGG](https://paperswithcode.com/method/vgg) loss is based on the [ReLU](https://paperswithcode.com/method/relu) activation layers of the pre-trained 19 layer VGG network. With $\\phi\\_{i,j}$ we indicate the feature map obtained by the $j$-th [convolution](https://paperswithcode.com/method/convolution) (after activation) before the $i$-th maxpooling layer within the VGG19 network, which we consider given. We then define the VGG loss as the euclidean distance between the feature representations of a reconstructed image $G\\_{\\theta\\_{G}}\\left(I^{LR}\\right)$ and the reference image $I^{HR}$:\r\n\r\n$$ l\\_{VGG/i.j} = \\frac{1}{W\\_{i,j}H\\_{i,j}}\\sum\\_{x=1}^{W\\_{i,j}}\\sum\\_{y=1}^{H\\_{i,j}}\\left(\\phi\\_{i,j}\\left(I^{HR}\\right)\\_{x, y} - \\phi\\_{i,j}\\left(G\\_{\\theta\\_{G}}\\left(I^{LR}\\right)\\right)\\_{x, y}\\right)^{2}$$ \r\n\r\nHere $W\\_{i,j}$ and $H\\_{i,j}$ describe the dimensions of the respective feature maps within the VGG network.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","paper":"/paper/photo-realistic-single-image-super-resolution","first_author":"Christian Ledig","n_authors":11,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/photo-realistic-single-image-super-resolution"},"source":{"url":"http://arxiv.org/abs/1609.04802v5","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/tensorlayer/srgan/blob/9721adce6a2ee51a56aaf0b319b89d35836f57e6/train.py#L124","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Loss Functions","url":"/methods/category/loss-functions","pwc_aliases":[]}],"n_papers_tagged":37,"archive_num_papers":37,"papers_newest_first":[{"paper":null,"slug":"2505-10589","title":"Super-Resolution Generative Adversarial Networks based Video Enhancement","date":"2025-05-14","arxiv_id":"2505.10589","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-estimation-for-super-resolution","title":"Uncertainty Estimation for Super-Resolution using ESRGAN","date":"2024-12-19","arxiv_id":"2412.15439","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-based-ckm-construction-with","slug":"deep-learning-based-ckm-construction-with","title":"Deep Learning-Based CKM Construction with Image Super-Resolution","date":"2024-10-28","arxiv_id":"2411.08887","n_code_links":1,"syntology":null},{"paper":null,"slug":"power-efficient-image-storage-leveraging","title":"Power-Efficient Image Storage: Leveraging Super Resolution Generative Adversarial Network for Sustainable Compression and Reduced Carbon Footprint","date":"2024-04-06","arxiv_id":"2404.04642","n_code_links":0,"syntology":null},{"paper":null,"slug":"fully-data-driven-model-for-increasing","title":"Fully Data-Driven Model for Increasing Sampling Rate Frequency of Seismic Data using Super-Resolution Generative Adversarial Networks","date":"2024-01-31","arxiv_id":"2402.00153","n_code_links":0,"syntology":null},{"paper":"/paper/target-oriented-domain-adaptation-for","slug":"target-oriented-domain-adaptation-for","title":"Texture and Noise Dual Adaptation for Infrared Image Super-Resolution","date":"2023-11-15","arxiv_id":"2311.08816","n_code_links":1,"syntology":null},{"paper":null,"slug":"guided-frequency-loss-for-image-restoration","title":"Guided Frequency Loss for Image Restoration","date":"2023-09-27","arxiv_id":"2309.15563","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-analysis-of-sr-gan-models","title":"A comparative analysis of SRGAN models","date":"2023-07-18","arxiv_id":"2307.09456","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-on-1-5t-3t-mri-conversion","title":"A Comparative Study on 1.5T-3T MRI Conversion through Deep Neural Network Models","date":"2022-10-12","arxiv_id":"2210.06362","n_code_links":0,"syntology":null},{"paper":"/paper/generative-adversarial-super-resolution-at","slug":"generative-adversarial-super-resolution-at","title":"Generative Adversarial Super-Resolution at the Edge with Knowledge Distillation","date":"2022-09-07","arxiv_id":"2209.03355","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextual-attention-mechanism-srgan-based","title":"Contextual Attention Mechanism, SRGAN Based Inpainting System for Eliminating Interruptions from Images","date":"2022-04-06","arxiv_id":"2204.02591","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-superresolution-using-scale-recurrent","title":"Image Superresolution using Scale-Recurrent Dense Network","date":"2022-01-28","arxiv_id":"2201.11998","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-resolution-pelvic-mri-reconstruction","title":"High-Resolution Pelvic MRI Reconstruction Using a Generative Adversarial Network with Attention and Cyclic Loss","date":"2021-07-21","arxiv_id":"2107.09989","n_code_links":0,"syntology":null},{"paper":"/paper/style-restricted-gan-multi-modal-translation","slug":"style-restricted-gan-multi-modal-translation","title":"Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks","date":"2021-05-17","arxiv_id":"2105.07621","n_code_links":1,"syntology":null},{"paper":null,"slug":"more-reliable-ai-solution-breast-ultrasound","title":"More Reliable AI Solution: Breast Ultrasound Diagnosis Using Multi-AI Combination","date":"2021-01-07","arxiv_id":"2101.02639","n_code_links":0,"syntology":null},{"paper":null,"slug":"super-resolution-guided-pore-detection-for","title":"Super-resolution Guided Pore Detection for Fingerprint Recognition","date":"2020-12-10","arxiv_id":"2012.05959","n_code_links":0,"syntology":null},{"paper":"/paper/fully-quantized-image-super-resolution","slug":"fully-quantized-image-super-resolution","title":"Fully Quantized Image Super-Resolution Networks","date":"2020-11-29","arxiv_id":"2011.14265","n_code_links":1,"syntology":null},{"paper":null,"slug":"micro-ct-image-assisted-cross-modality-super","title":"Micro CT Image-Assisted Cross Modality Super-Resolution of Clinical CT Images Utilizing Synthesized Training Dataset","date":"2020-10-20","arxiv_id":"2010.10207","n_code_links":0,"syntology":null},{"paper":"/paper/attaining-real-time-super-resolution-for","slug":"attaining-real-time-super-resolution-for","title":"Attaining Real-Time Super-Resolution for Microscopic Images Using GAN","date":"2020-10-09","arxiv_id":"2010.04634","n_code_links":1,"syntology":null},{"paper":"/paper/journey-towards-tiny-perceptual-super","slug":"journey-towards-tiny-perceptual-super","title":"Journey Towards Tiny Perceptual Super-Resolution","date":"2020-07-08","arxiv_id":"2007.04356","n_code_links":2,"syntology":null},{"paper":"/paper/perceptual-extreme-super-resolution-network","slug":"perceptual-extreme-super-resolution-network","title":"Perceptual Extreme Super Resolution Network with Receptive Field Block","date":"2020-05-26","arxiv_id":"2005.12597","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":"/paper/arbitrary-scale-super-resolution-for-brain","slug":"arbitrary-scale-super-resolution-for-brain","title":"Arbitrary Scale Super-Resolution for Brain MRI Images","date":"2020-04-05","arxiv_id":"2004.02086","n_code_links":1,"syntology":null},{"paper":null,"slug":"generator-from-edges-reconstruction-of-facial","title":"Generator From Edges: Reconstruction of Facial Images","date":"2020-02-16","arxiv_id":"2002.06682","n_code_links":0,"syntology":null},{"paper":"/paper/endol2h-deep-super-resolution-for-capsule","slug":"endol2h-deep-super-resolution-for-capsule","title":"EndoL2H: Deep Super-Resolution for Capsule Endoscopy","date":"2020-02-13","arxiv_id":"2002.05459","n_code_links":3,"syntology":null},{"paper":null,"slug":"an-application-of-generative-adversarial","title":"An Application of Generative Adversarial Networks for Super Resolution Medical Imaging","date":"2019-12-19","arxiv_id":"1912.09507","n_code_links":0,"syntology":null},{"paper":null,"slug":"anisotropic-super-resolution-in-prostate-mri","title":"Anisotropic Super Resolution in Prostate MRI using Super Resolution Generative Adversarial Networks","date":"2019-12-19","arxiv_id":"1912.09497","n_code_links":0,"syntology":null},{"paper":"/paper/image-super-resolution-using-a-wavelet-based","slug":"image-super-resolution-using-a-wavelet-based","title":"Image Super-Resolution Using a Wavelet-based Generative Adversarial Network","date":"2019-07-24","arxiv_id":"1907.10213","n_code_links":1,"syntology":null},{"paper":null,"slug":"boosting-resolution-and-recovering-texture-of","title":"Boosting Resolution and Recovering Texture of micro-CT Images with Deep Learning","date":"2019-07-15","arxiv_id":"1907.07131","n_code_links":0,"syntology":null},{"paper":"/paper/srgan-training-dataset-matters","slug":"srgan-training-dataset-matters","title":"SRGAN: Training Dataset Matters","date":"2019-03-24","arxiv_id":"1903.09922","n_code_links":1,"syntology":null},{"paper":"/paper/generative-collaborative-networks-for-single","slug":"generative-collaborative-networks-for-single","title":"Generative Collaborative Networks for Single Image Super-Resolution","date":"2019-02-27","arxiv_id":"1902.10467","n_code_links":1,"syntology":null},{"paper":null,"slug":"sredgenet-edge-enhanced-single-image-super","title":"SREdgeNet: Edge Enhanced Single Image Super Resolution using Dense Edge Detection Network and Feature Merge Network","date":"2018-12-18","arxiv_id":"1812.07174","n_code_links":0,"syntology":null},{"paper":null,"slug":"bi-gans-st-for-perceptual-image-super","title":"Bi-GANs-ST for Perceptual Image Super-resolution","date":"2018-11-01","arxiv_id":"1811.00367","n_code_links":0,"syntology":null},{"paper":null,"slug":"super-resolution-via-conditional-implicit","title":"Super-Resolution via Conditional Implicit Maximum Likelihood Estimation","date":"2018-10-02","arxiv_id":"1810.01406","n_code_links":0,"syntology":null},{"paper":"/paper/esrgan-enhanced-super-resolution-generative","slug":"esrgan-enhanced-super-resolution-generative","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","date":"2018-09-01","arxiv_id":"1809.00219","n_code_links":46,"syntology":{"ran":33,"of":44,"n_ran_checked":28,"n_instrument":5,"unverified":11,"pointer_only":7,"phrase":"33 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified","official":{"repos":["xinntao/ESRGAN"],"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/wide-activation-for-efficient-and-accurate","slug":"wide-activation-for-efficient-and-accurate","title":"Wide Activation for Efficient and Accurate Image Super-Resolution","date":"2018-08-27","arxiv_id":"1808.08718","n_code_links":12,"syntology":{"ran":9,"of":17,"n_ran_checked":9,"n_instrument":0,"unverified":8,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["JiahuiYu/wdsr_ntire2018"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/recovering-realistic-texture-in-image-super","slug":"recovering-realistic-texture-in-image-super","title":"Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform","date":"2018-04-09","arxiv_id":"1804.02815","n_code_links":4,"syntology":null},{"paper":"/paper/photo-realistic-single-image-super-resolution","slug":"photo-realistic-single-image-super-resolution","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","date":"2016-09-15","arxiv_id":"1609.04802","n_code_links":140,"syntology":{"ran":55,"of":72,"n_ran_checked":45,"n_instrument":10,"unverified":17,"pointer_only":14,"phrase":"55 ran (of which 0 constructed an object rather than computing a result; 45 with no instrument failure: 3 honoured, 3 violated, 39 with no contract checked; 10 where Syntology's instrument failed) · 17 unverified","official":null}}],"papers_shown":37,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":37,"with_a_code_link":17,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":37,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"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":4,"papers_where_code_ran_first_page":"/method/vgg-loss/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":"ran","page":1,"of":1,"url":"/method/vgg-loss/papers/ran/1","json":"/method/vgg-loss/papers/ran/1.json","rows":4}],"tasks":[{"task":"/task/super-resolution","name":"Super-Resolution","papers":34},{"task":"/task/image-super-resolution","name":"Image Super-Resolution","papers":23},{"task":null,"name":"Generative Adversarial Network","papers":14},{"task":"/task/ssim","name":"SSIM","papers":8},{"task":"/task/quantization","name":"Quantization","papers":2},{"task":"/task/video-super-resolution","name":"Video Super-Resolution","papers":2},{"task":"/task/brain-tumor-segmentation","name":"Brain Tumor Segmentation","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/data-compression","name":"Data Compression","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":1},{"task":"/task/edge-detection","name":"Edge Detection","papers":1},{"task":"/task/face-hallucination","name":"Face Hallucination","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-compression","name":"Image Compression","papers":1},{"task":"/task/image-enhancement","name":"Image Enhancement","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1}],"tasks_shown":20,"n_tasks":41,"usage_by_year":[{"year":"2016","papers":1},{"year":"2018","papers":6},{"year":"2019","papers":6},{"year":"2020","papers":9},{"year":"2021","papers":3},{"year":"2022","papers":4},{"year":"2023","papers":3},{"year":"2024","papers":4},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/vgg-loss"},"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=VGG%20Loss","read_at":"2026-10-05T01:03:38+00:00","query":"VGG Loss","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1609.04802","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'VGG Loss' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["VGG-Flow","RepOpt-VGG","VGG-MADiffRL"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"2c7e14df01ed63f4837cdb083ba1393b732a7173bece093d4669f889fffa6b2f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}