{"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/apply-hierarchical-chain-of-generation-to","title":"Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D Generation","arxiv_id":"2505.05505","date":"2025-05-07","proceeding":"CVPR 2025 1","authors":["Yiming Qin","Zhu Xu","Yang Liu"],"abstract":"Recent text-to-3D models can render high-quality assets, yet they still stumble on objects with complex attributes. The key obstacles are: (1) existing text-to-3D approaches typically lift text-to-image models to extract semantics via text encoders, while the text encoder exhibits limited comprehension ability for long descriptions, leading to deviated cross-attention focus, subsequently wrong attribute binding in generated results. (2) Occluded object parts demand a disciplined generation order and explicit part disentanglement. Though some works introduce manual efforts to alleviate the above issues, their quality is unstable and highly reliant on manual information. To tackle above problems, we propose a automated method Hierarchical-Chain-of-Generation (HCoG). It leverages a large language model to decompose the long description into blocks representing different object parts, and orders them from inside out according to occlusions, forming a hierarchical chain. Within each block we first coarsely create components, then precisely bind attributes via target-region localization and corresponding 3D Gaussian kernel optimization. Between blocks, we introduce Gaussian Extension and Label Elimination to seamlessly generate new parts by extending new Gaussian kernels, re-assigning semantic labels, and eliminating unnecessary kernels, ensuring that only relevant parts are added without disrupting previously optimized parts. Experiments confirm that HCoG yields structurally coherent, attribute-faithful 3D objects with complex attributes. The code is available at https://github.com/Wakals/GASCOL .","url_abs":"https://arxiv.org/abs/2505.05505v1","url_pdf":"https://arxiv.org/pdf/2505.05505v1.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":"apply-hierarchical-chain-of-generation-to","repo_url":"https://github.com/wakals/gascol","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"},{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"text-to-3d","task_name":"Text to 3D"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2505.05505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05505"}},"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":"deterministic:regex_extraction","url":"https://github.com/Wakals/GASCOL","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":"4ade5610ab000535","entry":"get_response","repo":"Wakals/GASCOL","repo_kind":"official","path":"threestudio/gpt/PE.py","file_url":"https://github.com/Wakals/GASCOL/blob/HEAD/threestudio/gpt/PE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4ade5610ab000535"}},{"code_sha256_prefix":"a738297eb782fb24","entry":"make_prompt","repo":"Wakals/GASCOL","repo_kind":"official","path":"threestudio/gpt/PE.py","file_url":"https://github.com/Wakals/GASCOL/blob/HEAD/threestudio/gpt/PE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a738297eb782fb24"}},{"code_sha256_prefix":"75a1916e578e12fe","entry":"get_chain","repo":"Wakals/GASCOL","repo_kind":"official","path":"threestudio/gpt/PE.py","file_url":"https://github.com/Wakals/GASCOL/blob/HEAD/threestudio/gpt/PE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"75a1916e578e12fe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}