{"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/gaussian-shell-maps-for-efficient-3d-human","title":"Gaussian Shell Maps for Efficient 3D Human Generation","arxiv_id":"2311.17857","date":"2023-11-29","proceeding":"CVPR 2024 1","authors":["Rameen Abdal","Wang Yifan","Zifan Shi","Yinghao Xu","Ryan Po","Zhengfei Kuang","Qifeng Chen","Dit-yan Yeung","Gordon Wetzstein"],"abstract":"Efficient generation of 3D digital humans is important in several industries, including virtual reality, social media, and cinematic production. 3D generative adversarial networks (GANs) have demonstrated state-of-the-art (SOTA) quality and diversity for generated assets. Current 3D GAN architectures, however, typically rely on volume representations, which are slow to render, thereby hampering the GAN training and requiring multi-view-inconsistent 2D upsamplers. Here, we introduce Gaussian Shell Maps (GSMs) as a framework that connects SOTA generator network architectures with emerging 3D Gaussian rendering primitives using an articulable multi shell--based scaffold. In this setting, a CNN generates a 3D texture stack with features that are mapped to the shells. The latter represent inflated and deflated versions of a template surface of a digital human in a canonical body pose. Instead of rasterizing the shells directly, we sample 3D Gaussians on the shells whose attributes are encoded in the texture features. These Gaussians are efficiently and differentiably rendered. The ability to articulate the shells is important during GAN training and, at inference time, to deform a body into arbitrary user-defined poses. Our efficient rendering scheme bypasses the need for view-inconsistent upsamplers and achieves high-quality multi-view consistent renderings at a native resolution of $512 \\times 512$ pixels. We demonstrate that GSMs successfully generate 3D humans when trained on single-view datasets, including SHHQ and DeepFashion.","url_abs":"https://arxiv.org/abs/2311.17857v1","url_pdf":"https://arxiv.org/pdf/2311.17857v1.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":"gaussian-shell-maps-for-efficient-3d-human","repo_url":"https://github.com/computational-imaging/GSM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.17857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17857"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/computational-imaging/GSM","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_draft_wrong":2,"ran_honours":3,"unverified":4},"by_repo_kind":{"official":{"samples":12,"ran":8,"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":12,"samples":[{"code_sha256_prefix":"eef98780cbfa6ee7","entry":"FOV_to_intrinsics","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/camera_utils.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/camera_utils.py","link_basis":"harvester_set","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":"eef98780cbfa6ee7"}},{"code_sha256_prefix":"a2b45afa097b55b6","entry":"file_ext","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/dataset_tool.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/dataset_tool.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a2b45afa097b55b6"}},{"code_sha256_prefix":"7682bd85198f0b32","entry":"get_video_files","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/gen_animation_videos.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/gen_animation_videos.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":"7682bd85198f0b32"}},{"code_sha256_prefix":"dd1dc700e87f36cc","entry":"maybe_min","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/dataset_tool.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/dataset_tool.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dd1dc700e87f36cc"}},{"code_sha256_prefix":"d01b68a634f71551","entry":"parse_comma_separated_list","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/calc_metrics.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/calc_metrics.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d01b68a634f71551"}},{"code_sha256_prefix":"f462255138c7700d","entry":"parse_range","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/gen_editing.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/gen_editing.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f462255138c7700d"}},{"code_sha256_prefix":"1116ca96f6d276ff","entry":"parse_tuple","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/dataset_tool.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/dataset_tool.py","link_basis":"harvester_set","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":"1116ca96f6d276ff"}},{"code_sha256_prefix":"180016b9227381b1","entry":"parse_vec2","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/gen_editing.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/gen_editing.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"180016b9227381b1"}},{"code_sha256_prefix":"9d31d2c4cd16bb2d","entry":"ask_yes_no","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/dnnlib/util.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/dnnlib/util.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":"9d31d2c4cd16bb2d"}},{"code_sha256_prefix":"fc49fa553c005268","entry":"compute_is","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/metrics/inception_score.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/metrics/inception_score.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":"fc49fa553c005268"}},{"code_sha256_prefix":"053fc534bc6bb989","entry":"format_time","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/dnnlib/util.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/dnnlib/util.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":"053fc534bc6bb989"}},{"code_sha256_prefix":"77f4aa0649e7f404","entry":"format_time_brief","repo":"computational-imaging/GSM","repo_kind":"official","path":"main/gsm/dnnlib/util.py","file_url":"https://github.com/computational-imaging/GSM/blob/HEAD/main/gsm/dnnlib/util.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":"77f4aa0649e7f404"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}