{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/s3im-stochastic-structural-similarity-and-its","title":"S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fields","arxiv_id":"2308.07032","date":"2023-08-14","proceeding":"ICCV 2023 1","authors":["Zeke Xie","Xindi Yang","Yujie Yang","Qi Sun","Yixiang Jiang","Haoran Wang","Yunfeng Cai","Mingming Sun"],"abstract":"Recently, Neural Radiance Field (NeRF) has shown great success in rendering novel-view images of a given scene by learning an implicit representation with only posed RGB images. NeRF and relevant neural field methods (e.g., neural surface representation) typically optimize a point-wise loss and make point-wise predictions, where one data point corresponds to one pixel. Unfortunately, this line of research failed to use the collective supervision of distant pixels, although it is known that pixels in an image or scene can provide rich structural information. To the best of our knowledge, we are the first to design a nonlocal multiplex training paradigm for NeRF and relevant neural field methods via a novel Stochastic Structural SIMilarity (S3IM) loss that processes multiple data points as a whole set instead of process multiple inputs independently. Our extensive experiments demonstrate the unreasonable effectiveness of S3IM in improving NeRF and neural surface representation for nearly free. The improvements of quality metrics can be particularly significant for those relatively difficult tasks: e.g., the test MSE loss unexpectedly drops by more than 90% for TensoRF and DVGO over eight novel view synthesis tasks; a 198% F-score gain and a 64% Chamfer $L_{1}$ distance reduction for NeuS over eight surface reconstruction tasks. Moreover, S3IM is consistently robust even with sparse inputs, corrupted images, and dynamic scenes.","url_abs":"https://arxiv.org/abs/2308.07032v1","url_pdf":"https://arxiv.org/pdf/2308.07032v1.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":"s3im-stochastic-structural-similarity-and-its","repo_url":"https://github.com/Madaoer/S3IM-Neural-Fields","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"},{"task_slug":"surface-reconstruction","task_name":"Surface Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.07032","atlas_url":"https://app.syntology.ai/?focus=2308.07032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07032"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Madaoer/S3IM-Neural-Fields","reach":null}],"summary":{"ran":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"2433c93f36594a19","entry":"S3IM","repo":"Madaoer/S3IM-Neural-Fields","repo_kind":"listed","path":"model_components/s3im.py","file_url":"https://github.com/Madaoer/S3IM-Neural-Fields/blob/HEAD/model_components/s3im.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2433c93f36594a19"}},{"code_sha256_prefix":"f2c9620464efabbd","entry":"SSIM","repo":"Madaoer/S3IM-Neural-Fields","repo_kind":"listed","path":"model_components/s3im.py","file_url":"https://github.com/Madaoer/S3IM-Neural-Fields/blob/HEAD/model_components/s3im.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2c9620464efabbd"}},{"code_sha256_prefix":"6154e3744ece5728","entry":"create_window","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6154e3744ece5728"}},{"code_sha256_prefix":"759aef07e871bf31","entry":"_ssim","repo":"Madaoer/S3IM-Neural-Fields","repo_kind":"listed","path":"model_components/s3im.py","file_url":"https://github.com/Madaoer/S3IM-Neural-Fields/blob/HEAD/model_components/s3im.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"759aef07e871bf31"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}