{"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":"/paper/ddp-diffusion-model-for-dense-visual","title":"DDP: Diffusion Model for Dense Visual Prediction","arxiv_id":"2303.17559","date":"2023-03-30","proceeding":"ICCV 2023 1","authors":["Yuanfeng Ji","Zhe Chen","Enze Xie","Lanqing Hong","Xihui Liu","Zhaoqiang Liu","Tong Lu","Zhenguo Li","Ping Luo"],"abstract":"We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. Our approach follows a \"noise-to-map\" generative paradigm for prediction by progressively removing noise from a random Gaussian distribution, guided by the image. The method, called DDP, efficiently extends the denoising diffusion process into the modern perception pipeline. Without task-specific design and architecture customization, DDP is easy to generalize to most dense prediction tasks, e.g., semantic segmentation and depth estimation. In addition, DDP shows attractive properties such as dynamic inference and uncertainty awareness, in contrast to previous single-step discriminative methods. We show top results on three representative tasks with six diverse benchmarks, without tricks, DDP achieves state-of-the-art or competitive performance on each task compared to the specialist counterparts. For example, semantic segmentation (83.9 mIoU on Cityscapes), BEV map segmentation (70.6 mIoU on nuScenes), and depth estimation (0.05 REL on KITTI). We hope that our approach will serve as a solid baseline and facilitate future research","url_abs":"https://arxiv.org/abs/2303.17559v2","url_pdf":"https://arxiv.org/pdf/2303.17559v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ddp-diffusion-model-for-dense-visual","repo_url":"https://github.com/jiyuanfeng/ddp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"DDP (Swin-L, step-3)","rank_in_archive_order":22,"of":79,"metrics":{"Delta < 1.25":"0.975","Delta < 1.25^2":"0.997","Delta < 1.25^3":"0.999","RMSE":"2.072","RMSE log":"0.076","Sq Rel":"0.148","absolute relative error":"0.050"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"DDP (step3)","rank_in_archive_order":41,"of":85,"metrics":{"Delta < 1.25":"0.921","Delta < 1.25^2":"0.990","Delta < 1.25^3":"0.998","RMSE":"0.329","absolute relative error":"0.094","log 10":"0.040"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-sun-rgbd","task":"Monocular Depth Estimation","dataset":"SUN-RGBD","model":"DDP (step-3)","rank_in_archive_order":3,"of":3,"metrics":{"Delta < 1.25":"0.825","Delta < 1.25^2":"0.973","Delta < 1.25^3":"0.994","RMSE":"0.397","absolute relative error":"0.128","log 10":"0.056"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"DDP (Swin-L, step-3)","rank_in_archive_order":60,"of":235,"metrics":{"Params (M)":"207","Validation mIoU":"54.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"DDP (ConvNeXt-L, step-3)","rank_in_archive_order":22,"of":99,"metrics":{"mIoU":"83.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.17559","atlas_url":"https://app.syntology.ai/?focus=2303.17559","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2303.17559"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.17559\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.17559"},"call":"get_concepts_for_paper(arxiv_id=\"2303.17559\")"}],"by_repo":[{"repo":"jiyuanfeng/ddp","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"71f3e3058800a5c691da26591163f991621cb7267b9dad5306ece189f2276486","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}