Iterative Geometry Encoding Volume for Stereo Matching

By Gangwei Xu, Xianqi Wang, Xiao-Hua Ding, Xin Yang. Computer Vision and Pattern Recognition, 2023

399 citations recorded by the source corpus.

Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in matching tasks. However, all-pairs correlations lack non-local geometry knowledge and have difficulties tackling local ambiguities in ill-posed regions. In this paper, we propose Iterative Geometry Encoding Volume (IGEV-Stereo), a new deep network architecture for stereo matching. The proposed IGEV-Stereo builds a combined geometry encoding volume that encodes geometry and context information as well as local matching details, and iteratively indexes it to update the disparity map. To speed up the convergence, we exploit GEV to regress an accurate starting point for ConvGRUs iterations. Our IGEV-Stereo ranks 1st on KITTI 2015 and 2012 (Reflective) among all published methods and is the fastest among the top 10 methods. In addition, IGEV-Stereo has strong cross-dataset generalization as well as high inference efficiency. We also extend our IGEV to multi-view stereo (MVS), i.e. IGEV-MVS, which achieves competitive accuracy on DTU benchmark. Code is available at https://github.com/gangweiX/IGEV.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/697e176d66a17c0b24613b8513ab951dc4112c34

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Hao Chen
2. J. Liew
3. Chi Zhang
4. Chunhua Shen
5. Wei Yin
6. Bingyi Kang
7. Zhipeng Cai
8. Gang Yu

In Computer Vision and Pattern Recognition

1. Chunhua Shen
2. Jiashi Feng
3. Luc Van Gool
4. Dacheng Tao
5. Xiaogang Wang
6. Trevor Darrell
7. Ming-Hsuan Yang
8. Gang Yu

Citations in the corpus

• Depth Anything 3: Recovering the Visual Space from Any Views (2025, positive): “On the dense side, cost-volume networks [106, 114] for MVS replaced hand-crafted regularization with 3D CNNs, improving depth accuracy especially at large baselines and thin structures compared with classical PatchMatch.”
• Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal Estimation (2024, positive): “Deep iterative refinement for geometry: Iterative refinement enables multi-step coarse-to-fine prediction and benefits a wide range of geometry estimation tasks, such as optical flow estimation [46], [75], [76], depth completion [43], [77], [78], and stereo matching [45], [79], [80].”