Research map / 3D vision / Depth and stereo
IGEV++: Iterative Multi-Range Geometry Encoding Volumes for Stereo Matching
Gangwei Xu, Xianqi Wang, Zhaoxing Zhang, Junda Cheng, Chunyuan Liao, Xin Yang
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 single-range geometry encoding volume (GEV) (ablation) | RAFT-Stereo baseline · Scene Flow Disp<192px | EPE: 0.54 -> 0.46 | Improved |
| replace GEV with multi-range GEV (MGEV) (ablation) | IGEV · Scene Flow Disp<768px | EPE: 0.84 -> 0.74 | Improved |
| add adaptive patch matching (APM) (ablation) | MGEV · Scene Flow Disp<768px | EPE: 0.74 -> 0.71 | Improved |
| add selective geometry feature fusion (SGFF) (ablation) | MGEV+APM · Scene Flow Disp<768px | EPE: 0.71 -> 0.67 | Improved |
| use only small-range GEV instead of multi-range (ablation) | IGEV++ · Scene Flow Disp<768px | EPE: 0.67 -> 1.06 | Hurt |
| use only large-range GEV instead of multi-range (ablation) | IGEV++ · Scene Flow Disp<192px | EPE: 0.43 -> 0.54 | Hurt |
| use only medium-range GEV instead of multi-range (ablation) | IGEV++ · Scene Flow Disp<384px | EPE: 0.56 -> 0.67 | Hurt |
| replace all-pairs correlation with MGEV, at 1 iteration | RAFT-Stereo · Scene Flow Disp<768px | EPE: 3.58 -> 0.97 | Improved |
| increase iterations from 16 to 32 | IGEV++ · Scene Flow Disp<768px | EPE: 0.67 -> 0.67 | No clear effect |
| extend cost volume to 768px disparity range | PCWNet · Scene Flow | EPE: 0.78 -> 1.52 | Hurt |
| use multi-range volumes instead of large cost volume | IGEV++ vs PCWNet · Scene Flow Disp<768px | memory (G): 11.62 -> 1.57 | Improved |
| use DepthAnythingV2-Large frozen backbone | IGEV++ · KITTI 2015 test | D1-all: 1.51 -> 1.43 | Improved |
Later papers that compared with this method
6 later accepted papers report IGEV as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- MonSter++: Unified Stereo Matching, Multi-View Stereo, and Real-Time Stereo With Monodepth Priors (TPAMI 2026 · better on 7 of 7 shared results)
- Geometry-Aware Stereo Matching via Monocular Disparity Distribution Prior and Gradient Enhancement (AAAI 2026 · better on 5 of 5 shared results)
- MonSter: Marry Monodepth to Stereo Unleashes Power (CVPR 2025 · better on 3 of 3 shared results)
- S2M2: Scalable Stereo Matching Model for Reliable Depth Estimation (ICCV 2025 · better on 3 of 3 shared results)
- RobuSTereo: Robust Zero-Shot Stereo Matching under Adverse Weather (ICCV 2025 · better on 1 of 1 shared result)
- Global Regulation and Excitation via Attention Tuning for Stereo Matching (ICCV 2025 · 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
- Iterative Geometry Encoding Volume for Stereo Matching (CVPR 2023 · similarity 0.94)
- Generalized Geometry Encoding Volume for Real-time Stereo Matching (AAAI 2026 · similarity 0.90)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.90)
- Accurate and Efficient Stereo Matching via Attention Concatenation Volume (TPAMI 2023 · similarity 0.90)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 2024 · similarity 0.88)
- IINet: Implicit Intra-inter Information Fusion for Real-Time Stereo Matching (AAAI 2024 · 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.
