Research map / 3D vision / Face and shape
SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views
Xiaoxiao Long, Cheng Lin, Peng Wang, Taku Komura, Wenping Wang
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 cascaded volumes instead of a single volume (ablation) | SparseNeuS (generic) · DTU ablation (3 views), generic | Chamfer distance: 1.80 -> 1.56 | Improved |
| add cascaded volumes instead of a single volume (ablation) | SparseNeuS (fine-tuning) · DTU ablation (3 views), fine-tuning | Chamfer distance: 1.32 -> 1.21 | Improved |
| add patch-based blending to pixel-based blending (ablation) | SparseNeuS fine-tuning · DTU ablation (3 views), fine-tuning | Chamfer distance: 1.39 -> 1.28 | Improved |
| add consistency-aware scheme in fine-tuning (ablation) | SparseNeuS fine-tuning · DTU ablation (3 views), fine-tuning | Chamfer distance: 1.28 -> 1.21 | Improved |
| initialize per-scene optimization with learned priors (ablation) | SparseNeuS fine-tuning · DTU per-scene optimization | Chamfer distance: 1.98 -> 1.65 | Improved |
| per-scene fine-tune the generic model | SparseNeuS · DTU (3 views) | Chamfer distance: 1.64 -> 1.27 | Improved |
| use SparseNeuS instead of MVSNerf in generic setting | SparseNeuS · DTU (3 views, generic) | Chamfer distance: 2.09 -> 1.64 | Improved |
| use SparseNeuS-ft instead of Colmap | SparseNeuS-ft · DTU (3 views, per-scene) | Chamfer distance: 1.52 -> 1.27 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Neus — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 1 of 1 shared result
- UniSurf — UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction (ICCV 2021) · 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
- NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views (AAAI 2024 · similarity 0.91)
- SC-NeuS: Consistent Neural Surface Reconstruction from Sparse and Noisy Views (AAAI 2024 · similarity 0.91)
- SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies (ICCV 2025 · similarity 0.91)
- UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets (CVPR 2024 · similarity 0.88)
- GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction (NeurIPS 2025 · similarity 0.88)
- Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views (AAAI 2024 · similarity 0.88)
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.
