{"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/v3d-video-diffusion-models-are-effective-3d","title":"V3D: Video Diffusion Models are Effective 3D Generators","arxiv_id":"2403.06738","date":"2024-03-11","proceeding":null,"authors":["Zilong Chen","Yikai Wang","Feng Wang","Zhengyi Wang","Huaping Liu"],"abstract":"Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video diffusion models, we introduce V3D, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation. To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator. Benefiting from this, the state-of-the-art video diffusion model could be fine-tuned to generate 360degree orbit frames surrounding an object given a single image. With our tailored reconstruction pipelines, we can generate high-quality meshes or 3D Gaussians within 3 minutes. Furthermore, our method can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views. Extensive experiments demonstrate the superior performance of the proposed approach, especially in terms of generation quality and multi-view consistency. Our code is available at https://github.com/heheyas/V3D","url_abs":"https://arxiv.org/abs/2403.06738v1","url_pdf":"https://arxiv.org/pdf/2403.06738v1.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":"v3d-video-diffusion-models-are-effective-3d","repo_url":"https://github.com/heheyas/v3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.06738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06738"}},"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/heheyas/v3d","reach":{"status":"ok"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"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":9,"samples":[{"code_sha256_prefix":"cfd6c8faf5e04937","entry":"blender2midas","repo":"heheyas/v3d","repo_kind":"official","path":"mesh_recon/datasets/v3d.py","file_url":"https://github.com/heheyas/v3d/blob/HEAD/mesh_recon/datasets/v3d.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":"cfd6c8faf5e04937"}},{"code_sha256_prefix":"45090c68bfc689c0","entry":"cast_rays","repo":"heheyas/v3d","repo_kind":"official","path":"mesh_recon/models/ray_utils.py","file_url":"https://github.com/heheyas/v3d/blob/HEAD/mesh_recon/models/ray_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":"45090c68bfc689c0"}},{"code_sha256_prefix":"456eeade4275ae9d","entry":"dot","repo":"heheyas/v3d","repo_kind":"official","path":"mesh_recon/models/utils.py","file_url":"https://github.com/heheyas/v3d/blob/HEAD/mesh_recon/models/utils.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":"456eeade4275ae9d"}},{"code_sha256_prefix":"33892b8f6d142c6d","entry":"get_activation","repo":"heheyas/v3d","repo_kind":"official","path":"mesh_recon/models/utils.py","file_url":"https://github.com/heheyas/v3d/blob/HEAD/mesh_recon/models/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":"33892b8f6d142c6d"}},{"code_sha256_prefix":"e098510a67655475","entry":"get_c2w_from_up_and_look_at","repo":"heheyas/v3d","repo_kind":"official","path":"mesh_recon/datasets/v3d.py","file_url":"https://github.com/heheyas/v3d/blob/HEAD/mesh_recon/datasets/v3d.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":"e098510a67655475"}},{"code_sha256_prefix":"b9a3f6cada33fe20","entry":"get_ortho_ray_directions_origins","repo":"heheyas/v3d","repo_kind":"official","path":"mesh_recon/models/ray_utils.py","file_url":"https://github.com/heheyas/v3d/blob/HEAD/mesh_recon/models/ray_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":"b9a3f6cada33fe20"}},{"code_sha256_prefix":"f46bcd572b96b7d4","entry":"get_ray_directions","repo":"heheyas/v3d","repo_kind":"official","path":"mesh_recon/models/ray_utils.py","file_url":"https://github.com/heheyas/v3d/blob/HEAD/mesh_recon/models/ray_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":"f46bcd572b96b7d4"}},{"code_sha256_prefix":"c09342b2879cc936","entry":"get_uniform_poses","repo":"heheyas/v3d","repo_kind":"official","path":"mesh_recon/datasets/v3d.py","file_url":"https://github.com/heheyas/v3d/blob/HEAD/mesh_recon/datasets/v3d.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":"c09342b2879cc936"}},{"code_sha256_prefix":"3cde7958baaeae2e","entry":"chunk_batch","repo":"heheyas/v3d","repo_kind":"official","path":"mesh_recon/models/utils.py","file_url":"https://github.com/heheyas/v3d/blob/HEAD/mesh_recon/models/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":"3cde7958baaeae2e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}