{"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/interfusion-text-driven-generation-of-3d","title":"InterFusion: Text-Driven Generation of 3D Human-Object Interaction","arxiv_id":"2403.15612","date":"2024-03-22","proceeding":null,"authors":["Sisi Dai","Wenhao Li","Haowen Sun","Haibin Huang","Chongyang Ma","Hui Huang","Kai Xu","Ruizhen Hu"],"abstract":"In this study, we tackle the complex task of generating 3D human-object interactions (HOI) from textual descriptions in a zero-shot text-to-3D manner. We identify and address two key challenges: the unsatisfactory outcomes of direct text-to-3D methods in HOI, largely due to the lack of paired text-interaction data, and the inherent difficulties in simultaneously generating multiple concepts with complex spatial relationships. To effectively address these issues, we present InterFusion, a two-stage framework specifically designed for HOI generation. InterFusion involves human pose estimations derived from text as geometric priors, which simplifies the text-to-3D conversion process and introduces additional constraints for accurate object generation. At the first stage, InterFusion extracts 3D human poses from a synthesized image dataset depicting a wide range of interactions, subsequently mapping these poses to interaction descriptions. The second stage of InterFusion capitalizes on the latest developments in text-to-3D generation, enabling the production of realistic and high-quality 3D HOI scenes. This is achieved through a local-global optimization process, where the generation of human body and object is optimized separately, and jointly refined with a global optimization of the entire scene, ensuring a seamless and contextually coherent integration. Our experimental results affirm that InterFusion significantly outperforms existing state-of-the-art methods in 3D HOI generation.","url_abs":"https://arxiv.org/abs/2403.15612v2","url_pdf":"https://arxiv.org/pdf/2403.15612v2.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":"interfusion-text-driven-generation-of-3d","repo_url":"https://github.com/sisidai/InterFusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"},{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"text-to-3d","task_name":"Text to 3D"},{"task_slug":"global-optimization","task_name":"global-optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.15612","atlas_url":"https://app.syntology.ai/?focus=2403.15612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15612"}},"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/sisidai/InterFusion","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"ran":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"1ce26f8dd9828d0f","entry":"pose_padding","repo":"sisidai/InterFusion","repo_kind":"official","path":"PoseGen/utils.py","file_url":"https://github.com/sisidai/InterFusion/blob/HEAD/PoseGen/utils.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1ce26f8dd9828d0f"}},{"code_sha256_prefix":"c014767b2812ccec","entry":"quaternion_to_angle_axis","repo":"sisidai/InterFusion","repo_kind":"official","path":"PoseGen/utils.py","file_url":"https://github.com/sisidai/InterFusion/blob/HEAD/PoseGen/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c014767b2812ccec"}},{"code_sha256_prefix":"31199aa07b56303f","entry":"rotation_matrix_to_angle_axis","repo":"sisidai/InterFusion","repo_kind":"official","path":"PoseGen/utils.py","file_url":"https://github.com/sisidai/InterFusion/blob/HEAD/PoseGen/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"31199aa07b56303f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}