# Non-local Recurrent Regularization Networks for Multi-view Stereo

arXiv: https://arxiv.org/abs/2110.06436 · HTML: https://mlsanity.com/paper/2110.06436/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 13 Oct 2021.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [DeepMVS: Learning Multi-view Stereopsis](https://mlsanity.com/paper/1804.00650/) (2018)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [PatchmatchNet: Learned Multi-View Patchmatch Stereo](https://mlsanity.com/paper/2012.01411/) (2020)
- [Learning a Multi-View Stereo Machine](https://mlsanity.com/paper/1708.05375/) (2017)
- [Cost Volume Pyramid Based Depth Inference for Multi-View Stereo](https://mlsanity.com/paper/1912.08329/) (2019)
- [Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness](https://mlsanity.com/paper/1911.12012/) (2019)
- [Point-Based Multi-View Stereo Network](https://mlsanity.com/paper/1908.04422/) (2019)
- [SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis](https://mlsanity.com/paper/1708.01749/) (2017)
- [Multi-Scale Geometric Consistency Guided Multi-View Stereo](https://mlsanity.com/paper/1904.08103/) (2019)
- [Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking](https://mlsanity.com/paper/2007.10872/) (2020)
- [Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume](https://mlsanity.com/paper/1912.11746/) (2019)
- [Planar Prior Assisted PatchMatch Multi-View Stereo](https://mlsanity.com/paper/1912.11744/) (2019)
- [Learned Multi-Patch Similarity](https://mlsanity.com/paper/1703.08836/) (2017)
- [Non-local Recurrent Neural Memory for Supervised Sequence Modeling](https://mlsanity.com/paper/1908.09535/) (2019)

## Built on by (most cited first, 6 of 6)

- [WT-MVSNet: Window-based Transformers for Multi-view Stereo](https://mlsanity.com/paper/2205.14319/) (2022)
- [GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo](https://mlsanity.com/paper/2310.19583/) (2023)
- [Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model](https://mlsanity.com/paper/2509.15220/) (2025)
- [Multi-View Stereo Representation Revisit: Region-Aware MVSNet](https://mlsanity.com/paper/2304.13614/) (2023)
- [Adaptive Stereo Depth Estimation with Multi-Spectral Images Across All Lighting Conditions](https://mlsanity.com/paper/2411.03638/) (2024)
- [Blending 3D Geometry and Machine Learning for Multi-View Stereopsis](https://mlsanity.com/paper/2505.03470/) (2025)

## Abstract (arXiv)

In deep multi-view stereo networks, cost regularization is crucial to achieve accurate depth estimation. Since 3D cost volume filtering is usually memory-consuming, recurrent 2D cost map regularization has recently become popular and has shown great potential in reconstructing 3D models of different scales. However, existing recurrent methods only model the local dependencies in the depth domain, which greatly limits the capability of capturing the global scene context along the depth dimension. To tackle this limitation, we propose a novel non-local recurrent regularization network for multi-view stereo, named NR2-Net. Specifically, we design a depth attention module to capture non-local depth interactions within a sliding depth block. Then, the global scene context between different blocks is modeled in a gated recurrent manner. This way, the long-range dependencies along the depth dimension are captured to facilitate the cost regularization. Moreover, we design a dynamic depth map fusion strategy to improve the algorithm robustness. Our method achieves state-of-the-art reconstruction results on both DTU and Tanks and Temples datasets.