{"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/generalizable-human-gaussians-for-sparse-view","title":"Generalizable Human Gaussians for Sparse View Synthesis","arxiv_id":"2407.12777","date":"2024-07-17","proceeding":null,"authors":["Youngjoong Kwon","Baole Fang","Yixing Lu","Haoye Dong","Cheng Zhang","Francisco Vicente Carrasco","Albert Mosella-Montoro","Jianjin Xu","Shingo Takagi","Daeil Kim","Aayush Prakash","Fernando de la Torre"],"abstract":"Recent progress in neural rendering has brought forth pioneering methods, such as NeRF and Gaussian Splatting, which revolutionize view rendering across various domains like AR/VR, gaming, and content creation. While these methods excel at interpolating {\\em within the training data}, the challenge of generalizing to new scenes and objects from very sparse views persists. Specifically, modeling 3D humans from sparse views presents formidable hurdles due to the inherent complexity of human geometry, resulting in inaccurate reconstructions of geometry and textures. To tackle this challenge, this paper leverages recent advancements in Gaussian Splatting and introduces a new method to learn generalizable human Gaussians that allows photorealistic and accurate view-rendering of a new human subject from a limited set of sparse views in a feed-forward manner. A pivotal innovation of our approach involves reformulating the learning of 3D Gaussian parameters into a regression process defined on the 2D UV space of a human template, which allows leveraging the strong geometry prior and the advantages of 2D convolutions. In addition, a multi-scaffold is proposed to effectively represent the offset details. Our method outperforms recent methods on both within-dataset generalization as well as cross-dataset generalization settings.","url_abs":"https://arxiv.org/abs/2407.12777v1","url_pdf":"https://arxiv.org/pdf/2407.12777v1.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":"generalizable-human-gaussians-for-sparse-view","repo_url":"https://github.com/humansensinglab/Generalizable-Human-Gaussians","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"neural-rendering","task_name":"Neural Rendering"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.12777","atlas_url":"https://app.syntology.ai/?focus=2407.12777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12777"}},"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/humansensinglab/Generalizable-Human-Gaussians","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"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":9,"samples":[{"code_sha256_prefix":"0b6a67d62274e07e","entry":"dilate","repo":"humansensinglab/Generalizable-Human-Gaussians","repo_kind":"official","path":"lib/ghg/network_eval.py","file_url":"https://github.com/humansensinglab/Generalizable-Human-Gaussians/blob/HEAD/lib/ghg/network_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b6a67d62274e07e"}},{"code_sha256_prefix":"b0c6d75bb1487c71","entry":"focal2fov","repo":"humansensinglab/Generalizable-Human-Gaussians","repo_kind":"official","path":"lib/graphics_utils.py","file_url":"https://github.com/humansensinglab/Generalizable-Human-Gaussians/blob/HEAD/lib/graphics_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b0c6d75bb1487c71"}},{"code_sha256_prefix":"c56b7ef16f309a45","entry":"gaussian","repo":"humansensinglab/Generalizable-Human-Gaussians","repo_kind":"official","path":"lib/loss.py","file_url":"https://github.com/humansensinglab/Generalizable-Human-Gaussians/blob/HEAD/lib/loss.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c56b7ef16f309a45"}},{"code_sha256_prefix":"616ba1e1fd6951b2","entry":"getProjectionMatrix","repo":"humansensinglab/Generalizable-Human-Gaussians","repo_kind":"official","path":"lib/graphics_utils.py","file_url":"https://github.com/humansensinglab/Generalizable-Human-Gaussians/blob/HEAD/lib/graphics_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"616ba1e1fd6951b2"}},{"code_sha256_prefix":"ac0e42d6fbcfbbe6","entry":"l1_loss","repo":"humansensinglab/Generalizable-Human-Gaussians","repo_kind":"official","path":"lib/loss.py","file_url":"https://github.com/humansensinglab/Generalizable-Human-Gaussians/blob/HEAD/lib/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ac0e42d6fbcfbbe6"}},{"code_sha256_prefix":"d73cfad5ab886ac4","entry":"read_img","repo":"humansensinglab/Generalizable-Human-Gaussians","repo_kind":"official","path":"lib/ghg/human_loader.py","file_url":"https://github.com/humansensinglab/Generalizable-Human-Gaussians/blob/HEAD/lib/ghg/human_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d73cfad5ab886ac4"}},{"code_sha256_prefix":"f424875683006127","entry":"repeat_interleave","repo":"humansensinglab/Generalizable-Human-Gaussians","repo_kind":"official","path":"lib/utils.py","file_url":"https://github.com/humansensinglab/Generalizable-Human-Gaussians/blob/HEAD/lib/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f424875683006127"}},{"code_sha256_prefix":"6c394c1d0cb69da4","entry":"getWorld2View2","repo":"humansensinglab/Generalizable-Human-Gaussians","repo_kind":"official","path":"lib/graphics_utils.py","file_url":"https://github.com/humansensinglab/Generalizable-Human-Gaussians/blob/HEAD/lib/graphics_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6c394c1d0cb69da4"}},{"code_sha256_prefix":"520a398e387edf23","entry":"sequence_loss","repo":"humansensinglab/Generalizable-Human-Gaussians","repo_kind":"official","path":"lib/loss.py","file_url":"https://github.com/humansensinglab/Generalizable-Human-Gaussians/blob/HEAD/lib/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"520a398e387edf23"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}