Research map / 3D vision / Face and shape
SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies
Liang Han, Xu Zhang, Haichuan Song, Kanle Shi, Yu-Shen Liu, Zhizhong Han
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 volume rendering-based feature consistency loss (ablation) | NeuS with color loss · DTU (3 small-overlapping views) | Chamfer Distance: 1.76 -> 1.47 | Improved |
| add uncertainty-guided depth constraint (ablation) | NeuS with color loss · DTU (3 small-overlapping views) | Chamfer Distance: 1.76 -> 1.62 | Improved |
| combine feature consistency and depth constraint (ablation) | NeuS with color loss · DTU (3 small-overlapping views) | Chamfer Distance: 1.47 -> 1.11 | Improved |
| add color consistency loss (warping) to NeuS baseline (ablation) | NeuS · DTU (3 small-overlapping views) | Chamfer Distance: 3.35 -> 1.76 | Improved |
| use uncertainty-guided depth loss with COLMAP calibration instead of MonoSDF-style depth loss (ablation) | SparseRecon · DTU (3 small-overlapping views) | Chamfer Distance: 1.59 -> 1.11 | Improved |
| use cosine feature similarity instead of L1 distance (ablation) | volume-rendering feature consistency · DTU (3 small-overlapping views) | Chamfer Distance: 2.36 -> 1.11 | Improved |
| use cosine feature similarity instead of L2 distance (ablation) | volume-rendering feature consistency · DTU (3 small-overlapping views) | Chamfer Distance: 1.81 -> 1.11 | Improved |
| compute feature consistency over all points along ray (volume rendering) instead of on-surface point only (ablation) | SparseRecon · DTU (3 small-overlapping views) | Chamfer Distance: 2.93 -> 1.11 | Improved |
| SparseRecon vs best prior overfitting/generalization method | SparseRecon · DTU (3 small-overlapping views) | mean Chamfer Distance: 1.39 -> 1.11 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 7 of 7 on most shared results.
- FatesGS — FatesGS: Fast and Accurate Sparse-View Surface Reconstruction Using Gaussian Splatting with Depth-Feature Consistency (AAAI 2025) · better on 1 of 1 shared result
- NeuSurf — NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views (AAAI 2024) · better on 1 of 1 shared result
- UFORecon — UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets (CVPR 2024) · better on 1 of 1 shared result
- SparseCraft — SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearization (ECCV 2024) · better on 1 of 1 shared result
- VolRecon — VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction (CVPR 2023) · better on 1 of 1 shared result
- ReTR — ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction (NeurIPS 2023) · better on 1 of 1 shared result
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 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
- UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets (CVPR 2024 · similarity 0.90)
- NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views (AAAI 2024 · similarity 0.90)
- GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstruction (AAAI 2025 · similarity 0.89)
- SC-NeuS: Consistent Neural Surface Reconstruction from Sparse and Noisy Views (AAAI 2024 · similarity 0.88)
- FatesGS: Fast and Accurate Sparse-View Surface Reconstruction Using Gaussian Splatting with Depth-Feature Consistency (AAAI 2025 · similarity 0.88)
- Sparis: Neural Implicit Surface Reconstruction of Indoor Scenes from Sparse Views (AAAI 2025 · 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.
