{"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/triposg-high-fidelity-3d-shape-synthesis","title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","arxiv_id":"2502.06608","date":"2025-02-10","proceeding":null,"authors":["Yangguang Li","Zi-Xin Zou","Zexiang Liu","Dehu Wang","Yuan Liang","Zhipeng Yu","Xingchao Liu","Yuan-Chen Guo","Ding Liang","Wanli Ouyang","Yan-Pei Cao"],"abstract":"Recent advancements in diffusion techniques have propelled image and video generation to unprecedented levels of quality, significantly accelerating the deployment and application of generative AI. However, 3D shape generation technology has so far lagged behind, constrained by limitations in 3D data scale, complexity of 3D data processing, and insufficient exploration of advanced techniques in the 3D domain. Current approaches to 3D shape generation face substantial challenges in terms of output quality, generalization capability, and alignment with input conditions. We present TripoSG, a new streamlined shape diffusion paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images. Specifically, we propose: 1) A large-scale rectified flow transformer for 3D shape generation, achieving state-of-the-art fidelity through training on extensive, high-quality data. 2) A hybrid supervised training strategy combining SDF, normal, and eikonal losses for 3D VAE, achieving high-quality 3D reconstruction performance. 3) A data processing pipeline to generate 2 million high-quality 3D samples, highlighting the crucial rules for data quality and quantity in training 3D generative models. Through comprehensive experiments, we have validated the effectiveness of each component in our new framework. The seamless integration of these parts has enabled TripoSG to achieve state-of-the-art performance in 3D shape generation. The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images. Moreover, TripoSG demonstrates improved versatility in generating 3D models from diverse image styles and contents, showcasing strong generalization capabilities. To foster progress and innovation in the field of 3D generation, we will make our model publicly available.","url_abs":"https://arxiv.org/abs/2502.06608v3","url_pdf":"https://arxiv.org/pdf/2502.06608v3.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":"triposg-high-fidelity-3d-shape-synthesis","repo_url":"https://github.com/VAST-AI-Research/TripoSG","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"triposg-high-fidelity-3d-shape-synthesis","repo_url":"https://github.com/tencent/flashvdm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"},{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"3d-shape-generation","task_name":"3D Shape Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.06608","atlas_url":"https://app.syntology.ai/?focus=2502.06608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06608"}},"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/tencent/flashvdm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/VAST-AI-Research/TripoSG","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"5ab4448f1f7e305b","entry":"compute_density_for_timestep_sampling","repo":"VAST-AI-Research/TripoSG","repo_kind":"official","path":"triposg/schedulers/scheduling_rectified_flow.py","file_url":"https://github.com/VAST-AI-Research/TripoSG/blob/HEAD/triposg/schedulers/scheduling_rectified_flow.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":"5ab4448f1f7e305b"}},{"code_sha256_prefix":"d6d82fbee7e27c98","entry":"compute_loss_weighting","repo":"VAST-AI-Research/TripoSG","repo_kind":"official","path":"triposg/schedulers/scheduling_rectified_flow.py","file_url":"https://github.com/VAST-AI-Research/TripoSG/blob/HEAD/triposg/schedulers/scheduling_rectified_flow.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":"d6d82fbee7e27c98"}},{"code_sha256_prefix":"069a7d354e6e9a86","entry":"find_candidates_band","repo":"VAST-AI-Research/TripoSG","repo_kind":"official","path":"triposg/inference_utils.py","file_url":"https://github.com/VAST-AI-Research/TripoSG/blob/HEAD/triposg/inference_utils.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":"069a7d354e6e9a86"}},{"code_sha256_prefix":"13d3ea2b443fb3a2","entry":"find_mesh_grid_coordinates_fast_gpu","repo":"VAST-AI-Research/TripoSG","repo_kind":"official","path":"triposg/inference_utils.py","file_url":"https://github.com/VAST-AI-Research/TripoSG/blob/HEAD/triposg/inference_utils.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":"13d3ea2b443fb3a2"}},{"code_sha256_prefix":"646b0cbdebda1982","entry":"generate_dense_grid_points_gpu","repo":"VAST-AI-Research/TripoSG","repo_kind":"official","path":"triposg/inference_utils.py","file_url":"https://github.com/VAST-AI-Research/TripoSG/blob/HEAD/triposg/inference_utils.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":"646b0cbdebda1982"}},{"code_sha256_prefix":"22b1f260da28f6a5","entry":"retrieve_timesteps","repo":"VAST-AI-Research/TripoSG","repo_kind":"official","path":"triposg/pipelines/pipeline_triposg.py","file_url":"https://github.com/VAST-AI-Research/TripoSG/blob/HEAD/triposg/pipelines/pipeline_triposg.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":"22b1f260da28f6a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}