{"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/uni4d-unifying-visual-foundation-models-for","title":"Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video","arxiv_id":"2503.21761","date":"2025-03-27","proceeding":"CVPR 2025 1","authors":["David Yifan Yao","Albert J. Zhai","Shenlong Wang"],"abstract":"This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising capabilities. However, training a single model for comprehensive 4D understanding remains challenging. We introduce Uni4D, a multi-stage optimization framework that harnesses multiple pretrained models to advance dynamic 3D modeling, including static/dynamic reconstruction, camera pose estimation, and dense 3D motion tracking. Our results show state-of-the-art performance in dynamic 4D modeling with superior visual quality. Notably, Uni4D requires no retraining or fine-tuning, highlighting the effectiveness of repurposing visual foundation models for 4D understanding.","url_abs":"https://arxiv.org/abs/2503.21761v1","url_pdf":"https://arxiv.org/pdf/2503.21761v1.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":"uni4d-unifying-visual-foundation-models-for","repo_url":"https://github.com/Davidyao99/uni4d","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"camera-pose-estimation","task_name":"Camera Pose Estimation"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"dynamic-reconstruction","task_name":"Dynamic Reconstruction"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.21761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21761"}},"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/Davidyao99/uni4d","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":17},"by_repo_kind":{"official":{"samples":18,"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":"000b3a2e5186a974","entry":"quaternion_to_matrix","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/variables.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/variables.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"000b3a2e5186a974"}},{"code_sha256_prefix":"6dc0a401faa181c2","entry":"absolute_error_loss","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/eval_depth.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/eval_depth.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":"6dc0a401faa181c2"}},{"code_sha256_prefix":"071060ffd8045cf0","entry":"absolute_value_scaling","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/eval_depth.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/eval_depth.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":"071060ffd8045cf0"}},{"code_sha256_prefix":"3470bb7f3951b38c","entry":"convert_trajectory_to_extrinsic_matrices","repo":"Davidyao99/uni4d","repo_kind":"official","path":"dataset_prepare/util.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/dataset_prepare/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":"3470bb7f3951b38c"}},{"code_sha256_prefix":"7d031b19941d06f5","entry":"depth2disparity","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/eval_depth.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/eval_depth.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":"7d031b19941d06f5"}},{"code_sha256_prefix":"a88685769d5ff548","entry":"depth_read","repo":"Davidyao99/uni4d","repo_kind":"official","path":"dataset_prepare/sintel_io.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/dataset_prepare/sintel_io.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":"a88685769d5ff548"}},{"code_sha256_prefix":"0cbc9f11c671557a","entry":"depth_vis","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/util.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/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":"0cbc9f11c671557a"}},{"code_sha256_prefix":"e162442d5908bd04","entry":"disparity_read","repo":"Davidyao99/uni4d","repo_kind":"official","path":"dataset_prepare/sintel_io.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/dataset_prepare/sintel_io.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":"e162442d5908bd04"}},{"code_sha256_prefix":"67bfa3f61f955ce1","entry":"fill_depth_nearest","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/util.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/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":"67bfa3f61f955ce1"}},{"code_sha256_prefix":"959323d9f907ca0b","entry":"find_closest_index","repo":"Davidyao99/uni4d","repo_kind":"official","path":"dataset_prepare/preprocess_tumd.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/dataset_prepare/preprocess_tumd.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":"959323d9f907ca0b"}},{"code_sha256_prefix":"0bf2c9084103deab","entry":"flow_norm","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/util.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/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":"0bf2c9084103deab"}},{"code_sha256_prefix":"a976c9053fc1681f","entry":"flow_read","repo":"Davidyao99/uni4d","repo_kind":"official","path":"dataset_prepare/sintel_io.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/dataset_prepare/sintel_io.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":"a976c9053fc1681f"}},{"code_sha256_prefix":"af61a94065b60b27","entry":"get_gt","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/eval_pose.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/eval_pose.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":"af61a94065b60b27"}},{"code_sha256_prefix":"d8e70a5c3026ef98","entry":"get_preds","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/eval_pose.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/eval_pose.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":"d8e70a5c3026ef98"}},{"code_sha256_prefix":"9ffd7c4d7dfde3e9","entry":"hat","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/variables.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/variables.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":"9ffd7c4d7dfde3e9"}},{"code_sha256_prefix":"339c20f5ac123bcc","entry":"read_trajectory","repo":"Davidyao99/uni4d","repo_kind":"official","path":"dataset_prepare/preprocess_tumd.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/dataset_prepare/preprocess_tumd.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":"339c20f5ac123bcc"}},{"code_sha256_prefix":"68275a37f3c13918","entry":"signed_expm1","repo":"Davidyao99/uni4d","repo_kind":"official","path":"uni4d/variables.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/uni4d/variables.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":"68275a37f3c13918"}},{"code_sha256_prefix":"b63ff70118c24067","entry":"transform44","repo":"Davidyao99/uni4d","repo_kind":"official","path":"dataset_prepare/preprocess_tumd.py","file_url":"https://github.com/Davidyao99/uni4d/blob/HEAD/dataset_prepare/preprocess_tumd.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":"b63ff70118c24067"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}