{"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/pixel2mesh-generating-3d-mesh-models-from","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","arxiv_id":"1804.01654","date":"2018-04-05","proceeding":"ECCV 2018 9","authors":["Nanyang Wang","yinda zhang","Zhuwen Li","Yanwei Fu","Wei Liu","Yu-Gang Jiang"],"abstract":"We propose an end-to-end deep learning architecture that produces a 3D shape\nin triangular mesh from a single color image. Limited by the nature of deep\nneural network, previous methods usually represent a 3D shape in volume or\npoint cloud, and it is non-trivial to convert them to the more ready-to-use\nmesh model. Unlike the existing methods, our network represents 3D mesh in a\ngraph-based convolutional neural network and produces correct geometry by\nprogressively deforming an ellipsoid, leveraging perceptual features extracted\nfrom the input image. We adopt a coarse-to-fine strategy to make the whole\ndeformation procedure stable, and define various of mesh related losses to\ncapture properties of different levels to guarantee visually appealing and\nphysically accurate 3D geometry. Extensive experiments show that our method not\nonly qualitatively produces mesh model with better details, but also achieves\nhigher 3D shape estimation accuracy compared to the state-of-the-art.","url_abs":"http://arxiv.org/abs/1804.01654v2","url_pdf":"http://arxiv.org/pdf/1804.01654v2.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":"pixel2mesh-generating-3d-mesh-models-from","repo_url":"https://github.com/nywang16/Pixel2Mesh","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pixel2mesh-generating-3d-mesh-models-from","repo_url":"https://github.com/richardsfc/pixel2mesh-ssds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pixel2mesh-generating-3d-mesh-models-from","repo_url":"https://github.com/ttaa9/genren","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pixel2mesh-generating-3d-mesh-models-from","repo_url":"https://github.com/xhxuciedu/3DHand","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pixel2mesh-generating-3d-mesh-models-from","repo_url":"https://github.com/Wapity/Pixel2Mesh-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-object-reconstruction","task_name":"3D Object Reconstruction"},{"task_slug":"3d-geometry","task_name":"3D geometry"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-reconstruction-on-data3dr2n2","task":"3D Object Reconstruction","dataset":"Data3D−R2N2","model":"Pixel2Mesh","rank_in_archive_order":12,"of":15,"metrics":{"Avg F1":"59.72"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.01654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.01654"}},"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/ttaa9/genren","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/richardsfc/pixel2mesh-ssds","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xhxuciedu/3DHand","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nywang16/Pixel2Mesh","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Wapity/Pixel2Mesh-Pytorch","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":11},"by_repo_kind":{"listed":{"samples":12,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"b190ef9c60b2629a","entry":"zeros","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"p2m/inits.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/p2m/inits.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b190ef9c60b2629a"}},{"code_sha256_prefix":"d336b18b019a3333","entry":"camera_info","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"GenerateData/3_camera_transform.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/GenerateData/3_camera_transform.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d336b18b019a3333"}},{"code_sha256_prefix":"25de61d1dac76cb8","entry":"camera_info","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"GenerateData/generate_data.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/GenerateData/generate_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"25de61d1dac76cb8"}},{"code_sha256_prefix":"6f7bdc31cdfaacc3","entry":"construct_feed_dict","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"p2m/utils.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/p2m/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6f7bdc31cdfaacc3"}},{"code_sha256_prefix":"f9a49c20298b14d3","entry":"generate_normal","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"GenerateData/2_generate_normal.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/GenerateData/2_generate_normal.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9a49c20298b14d3"}},{"code_sha256_prefix":"1b491f3f784b7cb0","entry":"glorot","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"p2m/inits.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/p2m/inits.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1b491f3f784b7cb0"}},{"code_sha256_prefix":"c2a076abe0d081bc","entry":"laplace_coord","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"p2m/losses.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/p2m/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2a076abe0d081bc"}},{"code_sha256_prefix":"e8df99f2ace67cd4","entry":"laplace_loss","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"p2m/losses.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/p2m/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e8df99f2ace67cd4"}},{"code_sha256_prefix":"f292c9b822ce4cfa","entry":"readFaceInfo","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"GenerateData/2_generate_normal.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/GenerateData/2_generate_normal.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f292c9b822ce4cfa"}},{"code_sha256_prefix":"b0d1b78daecde7e9","entry":"uniform","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"p2m/inits.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/p2m/inits.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b0d1b78daecde7e9"}},{"code_sha256_prefix":"ecfd96810a9fa29d","entry":"unit","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"p2m/losses.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/p2m/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ecfd96810a9fa29d"}},{"code_sha256_prefix":"a688e7eaa817d5c2","entry":"unit","repo":"nywang16/Pixel2Mesh","repo_kind":"listed","path":"GenerateData/2_generate_normal.py","file_url":"https://github.com/nywang16/Pixel2Mesh/blob/HEAD/GenerateData/2_generate_normal.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a688e7eaa817d5c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}