{"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/zero-1-to-3-zero-shot-one-image-to-3d-object","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","arxiv_id":"2303.11328","date":"2023-03-20","proceeding":"ICCV 2023 1","authors":["Ruoshi Liu","Rundi Wu","Basile Van Hoorick","Pavel Tokmakov","Sergey Zakharov","Carl Vondrick"],"abstract":"We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image. To perform novel view synthesis in this under-constrained setting, we capitalize on the geometric priors that large-scale diffusion models learn about natural images. Our conditional diffusion model uses a synthetic dataset to learn controls of the relative camera viewpoint, which allow new images to be generated of the same object under a specified camera transformation. Even though it is trained on a synthetic dataset, our model retains a strong zero-shot generalization ability to out-of-distribution datasets as well as in-the-wild images, including impressionist paintings. Our viewpoint-conditioned diffusion approach can further be used for the task of 3D reconstruction from a single image. Qualitative and quantitative experiments show that our method significantly outperforms state-of-the-art single-view 3D reconstruction and novel view synthesis models by leveraging Internet-scale pre-training.","url_abs":"https://arxiv.org/abs/2303.11328v1","url_pdf":"https://arxiv.org/pdf/2303.11328v1.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":"zero-1-to-3-zero-shot-one-image-to-3d-object","repo_url":"https://github.com/cvlab-columbia/zero123","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"image-to-3d","task_name":"Image to 3D"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"},{"task_slug":"single-view-3d-reconstruction","task_name":"Single-View 3D Reconstruction"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.11328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11328"}},"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/cvlab-columbia/zero123","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_draft_wrong":3,"ran_violates":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":0,"samples":[{"code_sha256_prefix":"c95e88aa409419d4","entry":"add_margin","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"zero123/ldm/util.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/zero123/ldm/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c95e88aa409419d4"}},{"code_sha256_prefix":"fe5dd5258046898c","entry":"always","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"zero123/ldm/modules/x_transformer.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/zero123/ldm/modules/x_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fe5dd5258046898c"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"zero123/ldm/modules/attention.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/zero123/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"zero123/ldm/models/diffusion/classifier.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/zero123/ldm/models/diffusion/classifier.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"zero123/ldm/modules/attention.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/zero123/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"1ee4e2eb0cf3a009","entry":"load_and_preprocess","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"zero123/ldm/util.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/zero123/ldm/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ee4e2eb0cf3a009"}},{"code_sha256_prefix":"f3cf3784fb4488db","entry":"tsr_stats","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"3drec/run_zero123.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/3drec/run_zero123.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3cf3784fb4488db"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"zero123/ldm/modules/attention.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/zero123/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}},{"code_sha256_prefix":"48b81cc9777a2a5b","entry":"load_im","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"3drec/run_zero123.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/3drec/run_zero123.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":"48b81cc9777a2a5b"}},{"code_sha256_prefix":"afe61ba472afc243","entry":"pil_rectangle_crop","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"zero123/ldm/util.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/zero123/ldm/util.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":"afe61ba472afc243"}},{"code_sha256_prefix":"5c2a4c571fbfbf59","entry":"sample_model","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"zero123/gradio_new.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/zero123/gradio_new.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":"5c2a4c571fbfbf59"}},{"code_sha256_prefix":"c3ba377c1bbf1281","entry":"sample_model","repo":"cvlab-columbia/zero123","repo_kind":"official","path":"zero123/gradio_objaverse.py","file_url":"https://github.com/cvlab-columbia/zero123/blob/HEAD/zero123/gradio_objaverse.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":"c3ba377c1bbf1281"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}