Research map / 3D vision / Face and shape
CPT-VR: Improving Surface Rendering via Closest Point Transform with View-Reflection Appearance
Zhipeng Hu, Yongqiang Zhang, Chen Liu, Lincheng Li, Sida Peng, Xiaowei Zhou, Changjie Fan, Xin Yu
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 |
|---|---|---|---|
| add reflection vector to IDR (ablation) | IDR · DTU | Chamfer Distance: 0.90 -> 1.68 | Hurt |
| add reflection vector to DMTet (ablation) | DMTet · DTU | Chamfer Distance: 1.24 -> 1.63 | Hurt |
| add reflection vector to CPT-VR with view vector (ablation) | CPT-VR · DTU | Chamfer Distance: 0.72 -> 0.65 | Improved |
| use reflection vector alone without view vector (ablation) | CPT-VR · DTU | Chamfer Distance: 0.65 -> 0.83 | Hurt |
| add depth supervision from CasMVSNet (ablation) | CPT-VR with one-point background · DTU | Chamfer Distance: 0.66 -> 0.59 | Improved |
| replace mask-based background with one-point background model (ablation) | CPT-VR · DTU | Chamfer Distance: 0.65 -> 0.66 | No clear effect |
| sample one background point at 2Fp rather than 1000Fp (ablation) | CPT-VR · DTU | Chamfer Distance: 0.73 -> 0.66 | Improved |
| increase background samples from 1 to 2 (ablation) | CPT-VR · DTU | Chamfer Distance: 0.66 -> 0.74 | Hurt |
| replace DMTet/IDR-style linear approximation with closest point transform | Surface rendering · DTU | mean Chamfer Distance: 0.71 -> 0.59 | Improved |
| rasterization-based rendering instead of volume rendering | CPT-VR vs NeuS2 · DTU | rendering time (s): 1.979 -> 0.057 | Improved |
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.
- NeuS2 — NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction (ICCV 2023) · better on 1 of 1 shared result
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
- Mesh Splatting for End-to-end Multiview Surface Reconstruction (ICLR 2026 · similarity 0.85)
- Differentiable Neural Surface Refinement for Modeling Transparent Objects (CVPR 2024 · similarity 0.85)
- Differentiable Point-based Inverse Rendering (CVPR 2024 · similarity 0.84)
- GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction (NeurIPS 2025 · similarity 0.84)
- OffsetOPT: Explicit Surface Reconstruction without Normals (CVPR 2025 · similarity 0.83)
- SpecTRe-GS: Modeling Highly Specular Surfaces with Reflected Nearby Objects by Tracing Rays in 3D Gaussian Splatting (CVPR 2025 · similarity 0.83)
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.
