{"work":{"id":"67aa4434-ef33-4b27-ae4f-1e5fa4225745","openalex_id":null,"doi":"10.48550/arxiv.2503.22236","arxiv_id":"2503.22236","raw_key":null,"title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","authors":null,"authors_text":"C","year":2025,"venue":"cs.GR","abstract":"With the growing demand for high-fidelity 3D models from 2D images, existing methods still face significant challenges in accurately reproducing fine-grained geometric details due to limitations in domain gaps and inherent ambiguities in RGB images. To address these issues, we propose Hi3DGen, a novel framework for generating high-fidelity 3D geometry from images via normal bridging. Hi3DGen consists of three key components: (1) an image-to-normal estimator that decouples the low-high frequency image pattern with noise injection and dual-stream training to achieve generalizable, stable, and sharp estimation; (2) a normal-to-geometry learning approach that uses normal-regularized latent diffusion learning to enhance 3D geometry generation fidelity; and (3) a 3D data synthesis pipeline that constructs a high-quality dataset to support training. Extensive experiments demonstrate the effectiveness and superiority of our framework in generating rich geometric details, outperforming state-of-the-art methods in terms of fidelity. Our work provides a new direction for high-fidelity 3D geometry generation from images by leveraging normal maps as an intermediate representation.","external_url":"https://arxiv.org/abs/2503.22236","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-10T12:15:01.137692+00:00","pith_arxiv_id":"2503.22236","created_at":"2026-05-11T10:06:05.560032+00:00","updated_at":"2026-07-10T12:15:01.137692+00:00","title_quality_ok":true,"display_title":"Hi3dgen: High-fidelity 3d geometry generation from images via normal bridging.arXiv preprint arXiv:2503.22236, 3:2","render_title":"Hi3dgen: High-fidelity 3d geometry generation from images via normal bridging.arXiv preprint arXiv:2503.22236, 3:2"},"hub":{"state":{"work_id":"67aa4434-ef33-4b27-ae4f-1e5fa4225745","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":18,"external_cited_by_count":null,"distinct_field_count":2,"first_pith_cited_at":"2025-12-16T18:58:28+00:00","last_pith_cited_at":"2026-07-07T17:59:50+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T15:49:46.087197+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}