Research map / 3D vision / Face and shape
Parametric SDF for Dynamic Surface Reconstruction
Chong Gao, Kai Ye, Qiyu Dai, Yiming Shao, Qiong Zeng, Ding Liang, Yanpei Cao, Guanbin Li, Wenzheng Chen
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 Fourier basis to polynomial-only basis (ablation) | p-SDF · basis composition ablation | PSNR (dB): 25.91 -> 36.34 | Improved |
| add polynomial basis to Fourier-only basis (ablation) | p-SDF · basis composition ablation | PSNR (dB): 35.90 -> 36.34 | Improved |
| use 96^3 grid instead of coarse 64^3 or costlier 128^3 (ablation) | p-SDF · grid resolution ablation | quality-cost trade-off | Mixed |
| increase Fourier bandwidth Nf (ablation) | p-SDF · Lego (fast motion) vs Toy (smooth) | geometry quality | Mixed |
| replace per-frame/incremental SDF (NeuS2) with parametric SDF curves | p-SDF · CMU Panoptic Studio | Chamfer Distance: 7.654 -> 0.026 | Improved |
| replace AT-GS with p-SDF | p-SDF · SynMotion-360 | PSNR: 32.671 -> 32.153 | Hurt |
| replace AT-GS with p-SDF | p-SDF · SynMotion-360 | LPIPS: 0.045 -> 0.028 | Improved |
| replace AT-GS with p-SDF | p-SDF · DiVa-360 | PSNR: 27.418 -> 27.584 | 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 6 of 7 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
- DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions (NeurIPS 2026 · similarity 0.90)
- 4DSurf: High-Fidelity Dynamic Scene Surface Reconstruction (CVPR 2026 · similarity 0.90)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.88)
- MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video (CVPR 2024 · similarity 0.87)
- Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation (CVPR 2025 · similarity 0.87)
- ReMatching Dynamic Reconstruction Flow (ICLR 2025 · similarity 0.86)
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.
