# Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness

arXiv: https://arxiv.org/abs/1911.12012 · HTML: https://mlsanity.com/paper/1911.12012/

## Key facts

- Cited by 151 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2019.

## Built on by (most cited first, 30 of 151)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022)
- [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024)
- [NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video](https://mlsanity.com/paper/2104.00681/) (2021)
- [GeoNeRF: Generalizing NeRF with Geometry Priors](https://mlsanity.com/paper/2111.13539/) (2021)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views](https://mlsanity.com/paper/2502.12138/) (2025)
- [NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images](https://mlsanity.com/paper/2305.17398/) (2023)
- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [Efficient Neural Radiance Fields for Interactive Free-viewpoint Video](https://mlsanity.com/paper/2112.01517/) (2021)
- [MeshLRM: Large Reconstruction Model for High-Quality Meshes](https://mlsanity.com/paper/2404.12385/) (2024)
- [Neural 3D Scene Reconstruction with the Manhattan-world Assumption](https://mlsanity.com/paper/2205.02836/) (2022)
- [TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers](https://mlsanity.com/paper/2111.14600/) (2021)
- [Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats](https://mlsanity.com/paper/2410.12781/) (2024)
- [NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction](https://mlsanity.com/paper/2203.11283/) (2022)
- [NeuTex: Neural Texture Mapping for Volumetric Neural Rendering](https://mlsanity.com/paper/2103.00762/) (2021)
- [Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation](https://mlsanity.com/paper/2201.01501/) (2022)
- [AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network](https://mlsanity.com/paper/2108.03824/) (2021)
- [Accurate and Efficient Stereo Matching via Attention Concatenation Volume](https://mlsanity.com/paper/2209.12699/) (2022)
- [Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra](https://mlsanity.com/paper/2304.09987/) (2023)
- [IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo](https://mlsanity.com/paper/2112.05126/) (2021)
- [Urban Radiance Field Representation with Deformable Neural Mesh Primitives](https://mlsanity.com/paper/2307.10776/) (2023)
- [LaRa: Efficient Large-Baseline Radiance Fields](https://mlsanity.com/paper/2407.04699/) (2024)
- [Multiview Stereo with Cascaded Epipolar RAFT](https://mlsanity.com/paper/2205.04502/) (2022)
- [MVSTER: Epipolar Transformer for Efficient Multi-View Stereo](https://mlsanity.com/paper/2204.07346/) (2022)
- [MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo](https://mlsanity.com/paper/2401.11673/) (2024)
- [Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry](https://mlsanity.com/paper/2112.08177/) (2021)
- [MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions](https://mlsanity.com/paper/2104.13325/) (2021)

## Abstract (arXiv)

We present Uncertainty-aware Cascaded Stereo Network (UCS-Net) for 3D reconstruction from multiple RGB images. Multi-view stereo (MVS) aims to reconstruct fine-grained scene geometry from multi-view images. Previous learning-based MVS methods estimate per-view depth using plane sweep volumes with a fixed depth hypothesis at each plane; this generally requires densely sampled planes for desired accuracy, and it is very hard to achieve high-resolution depth. In contrast, we propose adaptive thin volumes (ATVs); in an ATV, the depth hypothesis of each plane is spatially varying, which adapts to the uncertainties of previous per-pixel depth predictions. Our UCS-Net has three stages: the first stage processes a small standard plane sweep volume to predict low-resolution depth; two ATVs are then used in the following stages to refine the depth with higher resolution and higher accuracy. Our ATV consists of only a small number of planes; yet, it efficiently partitions local depth ranges within learned small intervals. In particular, we propose to use variance-based uncertainty estimates to adaptively construct ATVs; this differentiable process introduces reasonable and fine-grained spatial partitioning. Our multi-stage framework progressively subdivides the vast scene space with increasing depth resolution and precision, which enables scene reconstruction with high completeness and accuracy in a coarse-to-fine fashion. We demonstrate that our method achieves superior performance compared with state-of-the-art benchmarks on various challenging datasets.