Research map / 3D vision / Face and shape
SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearization
Mae Younes, Amine Ouasfi, Adnane Boukhayma
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 |
|---|---|---|---|
| Use Taylor-expansion losses instead of direct MVS point/normal supervision (ablation) | SparseCraft · DTU reconstruction (3 views) | Chamfer distance | Improved |
| Use input Taylor loss instead of only SDF zero supervision at MVS points (ablation) | SparseCraft · DTU reconstruction (3 views) | Chamfer distance | Improved |
| Add direct MVS supervision (especially normal loss) to baseline (ablation) | SparseCraft baseline · DTU reconstruction (3 views) | Chamfer distance | Improved |
| Add progressive hash encoding (ablation) | SparseCraft · DTU reconstruction and NVS | reconstruction artifacts / rendering quality | Improved |
| Add MVS geometric losses without progressive encoding (ablation) | SparseCraft · DTU novel view synthesis | rendering quality | Hurt |
| Combine MVS losses with progressive encoding (ablation) | SparseCraft · DTU novel view synthesis | rendering quality | Improved |
| Add both Taylor-based losses (ablation) | SparseCraft · DTU reconstruction (3 views) | Chamfer distance | Improved |
| Add MVS color regularization on diffuse component (ablation) | SparseCraft · DTU reconstruction and NVS | Chamfer distance / rendering quality | Improved |
| Replace COLMAP with CasMVSNet point clouds (ablation) | SparseCraft · DTU reconstruction (3 views) | Chamfer distance | Improved |
Later papers that compared with this method
6 later accepted papers report SparseCraft as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction (AAAI 2026 · better on 2 of 2 shared results)
- Generalizable Neural Reconstruction of High-Fidelity Surfaces via Sparse Volumetric Representations (ECCV 2026 · better on 2 of 2 shared results)
- Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priors (ECCV 2026 · better on 1 of 1 shared result)
- Sparfels: Fast Reconstruction from Sparse Unposed Imagery (ICCV 2025 · better on 2 of 2 shared results)
- Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views (CVPR 2025 · better on 0 of 1 shared result)
- SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies (ICCV 2025 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- FreeNeRF — FreeNeRF: Improving Few-Shot Neural Rendering With Free Frequency Regularization (CVPR 2023) · better on 5 of 5 shared results
- FlipNeRF — FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis (ICCV 2023) · better on 4 of 4 shared results
- 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
- Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views (AAAI 2024 · similarity 0.89)
- Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering (CVPR 2025 · similarity 0.87)
- LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields (CVPR 2025 · similarity 0.87)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.87)
- Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views (CVPR 2025 · similarity 0.87)
- ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining (CVPR 2024 · similarity 0.87)
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.
