{"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/epidiff-enhancing-multi-view-synthesis-via","title":"EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion","arxiv_id":"2312.06725","date":"2023-12-11","proceeding":"CVPR 2024 1","authors":["Zehuan Huang","Hao Wen","Junting Dong","Yaohui Wang","Yangguang Li","Xinyuan Chen","Yan-Pei Cao","Ding Liang","Yu Qiao","Bo Dai","Lu Sheng"],"abstract":"Generating multiview images from a single view facilitates the rapid generation of a 3D mesh conditioned on a single image. Recent methods that introduce 3D global representation into diffusion models have shown the potential to generate consistent multiviews, but they have reduced generation speed and face challenges in maintaining generalizability and quality. To address this issue, we propose EpiDiff, a localized interactive multiview diffusion model. At the core of the proposed approach is to insert a lightweight epipolar attention block into the frozen diffusion model, leveraging epipolar constraints to enable cross-view interaction among feature maps of neighboring views. The newly initialized 3D modeling module preserves the original feature distribution of the diffusion model, exhibiting compatibility with a variety of base diffusion models. Experiments show that EpiDiff generates 16 multiview images in just 12 seconds, and it surpasses previous methods in quality evaluation metrics, including PSNR, SSIM and LPIPS. Additionally, EpiDiff can generate a more diverse distribution of views, improving the reconstruction quality from generated multiviews. Please see our project page at https://huanngzh.github.io/EpiDiff/.","url_abs":"https://arxiv.org/abs/2312.06725v3","url_pdf":"https://arxiv.org/pdf/2312.06725v3.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":"epidiff-enhancing-multi-view-synthesis-via","repo_url":"https://github.com/huanngzh/EpiDiff","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"ssim","task_name":"SSIM"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.06725","atlas_url":"https://app.syntology.ai/?focus=2312.06725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06725"}},"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/huanngzh/EpiDiff","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"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":"daafc1c89511b8be","entry":"normalization","repo":"huanngzh/EpiDiff","repo_kind":"official","path":"epidiff/models/blocks/resnet.py","file_url":"https://github.com/huanngzh/EpiDiff/blob/HEAD/epidiff/models/blocks/resnet.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"daafc1c89511b8be"}},{"code_sha256_prefix":"129b804760b3115f","entry":"zero_module","repo":"huanngzh/EpiDiff","repo_kind":"official","path":"epidiff/models/blocks/resnet.py","file_url":"https://github.com/huanngzh/EpiDiff/blob/HEAD/epidiff/models/blocks/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"129b804760b3115f"}},{"code_sha256_prefix":"c596e50230fd9ed8","entry":"checkpoint","repo":"huanngzh/EpiDiff","repo_kind":"official","path":"epidiff/models/blocks/transformer.py","file_url":"https://github.com/huanngzh/EpiDiff/blob/HEAD/epidiff/models/blocks/transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c596e50230fd9ed8"}},{"code_sha256_prefix":"fe4eb545bbb728e0","entry":"conv_nd","repo":"huanngzh/EpiDiff","repo_kind":"official","path":"epidiff/models/blocks/resnet.py","file_url":"https://github.com/huanngzh/EpiDiff/blob/HEAD/epidiff/models/blocks/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fe4eb545bbb728e0"}},{"code_sha256_prefix":"a362e5b7a1be4609","entry":"get_down_block","repo":"huanngzh/EpiDiff","repo_kind":"official","path":"epidiff/models/blocks/unet_blocks.py","file_url":"https://github.com/huanngzh/EpiDiff/blob/HEAD/epidiff/models/blocks/unet_blocks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a362e5b7a1be4609"}},{"code_sha256_prefix":"01feceecb56a7ffb","entry":"get_up_block","repo":"huanngzh/EpiDiff","repo_kind":"official","path":"epidiff/models/blocks/unet_blocks.py","file_url":"https://github.com/huanngzh/EpiDiff/blob/HEAD/epidiff/models/blocks/unet_blocks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01feceecb56a7ffb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}