# ReDT: Resolution-Decoupled Visual Geometry Transformer

arXiv: https://arxiv.org/abs/2610.25517 · HTML: https://mlsanity.com/paper/2610.25517/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Sparse-input reconstruction, one of 15 directions in 3D reconstruction and neural rendering.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 18 Oct 2026.

## Placed in

- 3D reconstruction and neural rendering / [Sparse-input reconstruction](https://mlsanity.com/recon3d/sparse-input-reconstruction/)

## Builds on (most cited first, 24 of 24)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [DeepMVS: Learning Multi-view Stereopsis](https://mlsanity.com/paper/1804.00650/) (2018)
- [Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo](https://mlsanity.com/paper/2303.01943/) (2023)
- [DynamicStereo: Consistent Dynamic Depth from Stereo Videos](https://mlsanity.com/paper/2305.02296/) (2023)
- [DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training](https://mlsanity.com/paper/2403.03542/) (2024)
- [SMD-Nets: Stereo Mixture Density Networks](https://mlsanity.com/paper/2104.03866/) (2021)
- [Continuum Attention for Neural Operators](https://mlsanity.com/paper/2406.06486/) (2024)
- [SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data](https://mlsanity.com/paper/2105.08612/) (2021)
- [ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training](https://mlsanity.com/paper/2603.04385/) (2026)
- [VGG-T3: Offline Feed-Forward 3D Reconstruction at Scale](https://mlsanity.com/paper/2602.23361/) (2026)
- [FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention](https://mlsanity.com/paper/2512.01540/) (2025)
- [Geometric Action Model for Robot Policy Learning](https://mlsanity.com/paper/2606.17046/) (2026)
- [VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency](https://mlsanity.com/paper/2602.05508/) (2026)
- [Simple yet Effective: Low-Rank Spatial Attention for Neural Operators](https://mlsanity.com/paper/2604.03582/) (2026)
- [HD-VGGT: High-Resolution Visual Geometry Transformer](https://mlsanity.com/paper/2603.27222/) (2026)
- [TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention](https://mlsanity.com/paper/2605.14315/) (2026)
- [Functional Attention: From Pairwise Affinities to Functional Correspondences](https://mlsanity.com/paper/2605.31559/) (2026)
- [Learning Orthonormal Bases for Function Spaces](https://mlsanity.com/paper/2605.19959/) (2026)

## Abstract (arXiv)

We introduce ReDT, a feed-forward visual geometry transformer designed to scale multi-view reconstruction to high-definition (HD) inputs. Existing visual geometry transformers are typically trained at fixed, standard definition (SD) resolutions and exhibit degraded reconstruction quality and poor computational scaling to high input resolutions. While recent efficient architectures reduce the complexity of inter-frame attention, expensive intra-frame and encoder attention remain largely unaddressed, making HD reconstruction impractical with existing architectures. ReDT addresses both limitations with a resolution-aware architecture designed to scale to high-resolution inputs. The key idea of ReDT is to first map each view to a fixed-size set of basis tokens, compute correspondences in this compact constant-size basis space, and then project the outputs back to the original resolution for dense prediction. By decoupling the internal representation from input resolution during attention, ReDT substantially reduces the computational cost of high-resolution 3D reconstruction and improves model performance at all resolutions. Extensive experiments on multiple datasets spanning SD to FHD (2K) show that ReDT outperforms state-of-the-art visual geometry transformers in both reconstruction quality and computational efficiency. For instance, on the ETH3D (2K) dataset, ReDT achieves a 16× speedup, a 34% reduction in peak GPU memory usage, and a 33% reduction in chamfer distance over VGGT-Omega. hrefhttps://redt.github.ioProject Website.