Research map / 3D vision / 3D generation
ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction
Yixun Liang, Hao He, Ying-Cong 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 occlusion transformer to render transformer (ablation) | ReTR · DTU sparse view | chamfer distance: 1.31 -> 1.28 | Improved |
| add hybrid extractor to render transformer (ablation) | ReTR · DTU sparse view | chamfer distance: 1.31 -> 1.29 | Improved |
| add both occlusion transformer and hybrid extractor (ablation) | ReTR · DTU sparse view | chamfer distance: 1.31 -> 1.17 | Improved |
| use continuous positional encoding instead of traditional (ablation) | ReTR · DTU sparse view, (64,64) samples | chamfer distance: 1.18 -> 1.17 | Improved |
| use continuous positional encoding, (64,0) samples (ablation) | ReTR · DTU sparse view | chamfer distance: 1.26 -> 1.22 | Improved |
| reduce sample points from (64,64) to (16,16) (ablation) | ReTR · DTU sparse view | chamfer distance: 1.17 -> 1.30 | Hurt |
| reduce sample points from (64,64) to (16,16) (ablation) | VolRecon · DTU sparse view | chamfer distance: 1.38 -> 1.60 | Hurt |
| increase coarse sampling to (128,0) (ablation) | VolRecon · DTU sparse view | chamfer distance: 1.45 -> 1.79 | Hurt |
| remove depth loss for unsupervised training (ablation) | ReTR · DTU sparse view | chamfer distance: 1.17 -> 1.45 | Hurt |
| remove depth loss (ablation) | VolRecon · DTU sparse view | chamfer distance: 1.38 -> 2.06 | Hurt |
| remove depth loss (ablation) | SparseNeuS · DTU sparse view | chamfer distance: 4.22 -> 1.96 | Improved |
| learning-based rendering transformer vs VolRecon volume rendering | ReTR · DTU sparse view | mean chamfer distance: 1.38 -> 1.17 | Improved |
Later papers that compared with this method
8 later accepted papers report ReTR as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.
- 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)
- GSRecon: Efficient Generalizable Gaussian Splatting for Surface Reconstruction from Sparse Views (ICCV 2025 · better on 2 of 2 shared results)
- SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies (ICCV 2025 · better on 1 of 1 shared result)
- Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields (ECCV 2024 · better on 3 of 3 shared results)
- UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets (CVPR 2024 · better on 2 of 2 shared results)
- Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction (ECCV 2024 · better on 1 of 1 shared result)
- SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearization (ECCV 2024 · 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 3 of 3 on most shared results.
- VolRecon — VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction (CVPR 2023) · better on 7 of 7 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
- ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting (ICCV 2023 · similarity 0.89)
- Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction (ICLR 2023 · similarity 0.89)
- Differentiable Neural Surface Refinement for Modeling Transparent Objects (CVPR 2024 · similarity 0.88)
- SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views (ECCV 2022 · similarity 0.88)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · similarity 0.88)
- LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields (CVPR 2025 · 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.
