Research map / 3D vision / Depth and stereo
GCRayDiffusion: Pose-Free Surface Reconstruction via Geometric Consistent Ray Diffusion
Li-Heng Chen, Zi-Xin Zou, Chang Liu, Tianjiao Jing, Yan-Pei Cao, Shi-Sheng Huang, Hongbo Fu, Hua Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| condition ray diffusion denoiser on triplane SDF (ablation) | GCRayDiffusion · Objaverse, 4 images | camera rotation accuracy (%): 86.3 -> 92.32 | Improved |
| condition ray diffusion denoiser on triplane SDF (ablation) | GCRayDiffusion · Objaverse, 4 images | camera translation accuracy (%): 37.5 -> 62.62 | Improved |
| guide triplane SDF learning with ray diffusion sampling points (on-surface regularization) (ablation) | GCRayDiffusion · Objaverse | Hausdorff Distance: 0.802 -> 0.323 | Improved |
| guide triplane SDF learning with ray diffusion sampling points (ablation) | GCRayDiffusion · Objaverse | F-score: 0.988 -> 0.99 | No clear effect |
| GCRayDiffusion vs DUSt3R on GSO 4-image rotation accuracy | GCRayDiffusion · GSO, 4 images | camera rotation accuracy (%): 92.37 vs 91.35 | Hurt |
| GCRayDiffusion vs DUSt3R on GSO F-score | GCRayDiffusion · GSO surface reconstruction | F-score: 0.961 vs 0.958 | Hurt |
| GCRayDiffusion vs best baseline on Objaverse 2-image rotation accuracy | GCRayDiffusion · Objaverse, 2 images | camera rotation accuracy (%): 90.52 -> 93.21 | Improved |
| increase number of input images from 4 to 6 for diffusion baselines | RayDiffusion · Objaverse | camera rotation accuracy (%): 87.20 -> 79.39 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DUSt3R — DUSt3R: Geometric 3D Vision Made Easy (CVPR 2024) · better on 7 of 9 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Cameras as Rays: Pose Estimation via Ray Diffusion (ICLR 2024 · similarity 0.90)
- CRAYM: Neural Field Optimization via Camera RAY Matching (NeurIPS 2024 · similarity 0.88)
- Coherent 3D Scene Diffusion From a Single RGB Image (NeurIPS 2024 · similarity 0.87)
- DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion (CVPR 2025 · similarity 0.86)
- Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion (CVPR 2025 · similarity 0.86)
- Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
