{"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/mvdiffusion-enabling-holistic-multi-view-1","title":"MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion","arxiv_id":"2307.01097","date":"2023-07-03","proceeding":"NeurIPS 2023 11","authors":["Shitao Tang","Fuyang Zhang","Jiacheng Chen","Peng Wang","Yasutaka Furukawa"],"abstract":"This paper introduces MVDiffusion, a simple yet effective method for generating consistent multi-view images from text prompts given pixel-to-pixel correspondences (e.g., perspective crops from a panorama or multi-view images given depth maps and poses). Unlike prior methods that rely on iterative image warping and inpainting, MVDiffusion simultaneously generates all images with a global awareness, effectively addressing the prevalent error accumulation issue. At its core, MVDiffusion processes perspective images in parallel with a pre-trained text-to-image diffusion model, while integrating novel correspondence-aware attention layers to facilitate cross-view interactions. For panorama generation, while only trained with 10k panoramas, MVDiffusion is able to generate high-resolution photorealistic images for arbitrary texts or extrapolate one perspective image to a 360-degree view. For multi-view depth-to-image generation, MVDiffusion demonstrates state-of-the-art performance for texturing a scene mesh.","url_abs":"https://arxiv.org/abs/2307.01097v7","url_pdf":"https://arxiv.org/pdf/2307.01097v7.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":"mvdiffusion-enabling-holistic-multi-view-1","repo_url":"https://github.com/Tangshitao/MVDiffusion","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.01097","atlas_url":"https://app.syntology.ai/?focus=2307.01097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01097"}},"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/Tangshitao/MVDiffusion","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"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":10,"samples":[{"code_sha256_prefix":"17e606b60296442a","entry":"BasicTransformerBlock","repo":"Tangshitao/MVDiffusion","repo_kind":"official","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.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":"17e606b60296442a"}},{"code_sha256_prefix":"105b547188750534","entry":"CrossAttention","repo":"Tangshitao/MVDiffusion","repo_kind":"official","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.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":"105b547188750534"}},{"code_sha256_prefix":"41c0a6b2499f6bc0","entry":"FeedForward","repo":"Tangshitao/MVDiffusion","repo_kind":"official","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.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":"41c0a6b2499f6bc0"}},{"code_sha256_prefix":"f5892d0d67314a54","entry":"PosEmbedding","repo":"Tangshitao/MVDiffusion","repo_kind":"official","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.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":"f5892d0d67314a54"}},{"code_sha256_prefix":"3bb314f8e5f121c3","entry":"get_correspondences","repo":"Tangshitao/MVDiffusion","repo_kind":"official","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3bb314f8e5f121c3"}},{"code_sha256_prefix":"85b4b8782d314094","entry":"get_x_2d","repo":"Tangshitao/MVDiffusion","repo_kind":"official","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"85b4b8782d314094"}},{"code_sha256_prefix":"a3afa33cd4694dbf","entry":"CPAttn","repo":"Tangshitao/MVDiffusion","repo_kind":"official","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.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":"a3afa33cd4694dbf"}},{"code_sha256_prefix":"43b2e9563753c165","entry":"MultiViewBaseModel","repo":"Tangshitao/MVDiffusion","repo_kind":"official","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.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":"43b2e9563753c165"}},{"code_sha256_prefix":"e8c158d66b578394","entry":"get_key_value","repo":"Tangshitao/MVDiffusion","repo_kind":"official","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.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":"e8c158d66b578394"}},{"code_sha256_prefix":"9ac92407ea4b7ad8","entry":"get_query_value","repo":"Tangshitao/MVDiffusion","repo_kind":"official","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.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":"9ac92407ea4b7ad8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}