{"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/instructscene-instruction-driven-3d-indoor","title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","arxiv_id":"2402.04717","date":"2024-02-07","proceeding":null,"authors":["Chenguo Lin","Yadong Mu"],"abstract":"Comprehending natural language instructions is a charming property for 3D indoor scene synthesis systems. Existing methods directly model object joint distributions and express object relations implicitly within a scene, thereby hindering the controllability of generation. We introduce InstructScene, a novel generative framework that integrates a semantic graph prior and a layout decoder to improve controllability and fidelity for 3D scene synthesis. The proposed semantic graph prior jointly learns scene appearances and layout distributions, exhibiting versatility across various downstream tasks in a zero-shot manner. To facilitate the benchmarking for text-driven 3D scene synthesis, we curate a high-quality dataset of scene-instruction pairs with large language and multimodal models. Extensive experimental results reveal that the proposed method surpasses existing state-of-the-art approaches by a large margin. Thorough ablation studies confirm the efficacy of crucial design components. Project page: https://chenguolin.github.io/projects/InstructScene.","url_abs":"https://arxiv.org/abs/2402.04717v1","url_pdf":"https://arxiv.org/pdf/2402.04717v1.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":"instructscene-instruction-driven-3d-indoor","repo_url":"https://github.com/chenguolin/InstructScene","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"indoor-scene-synthesis","task_name":"Indoor Scene Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.04717","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}