Results for CMRA-Stereo
Submission data
| Full name | Cost-Conditioned Multi-Receptive-Field Residual Aggregation for Stereo Matching |
| Description | CMRA-Stereo is a stereo matching framework developed for accurate and efficient depth estimation in challenging visual environments. Our research focuses on robust stereo perception, including applications in underwater robotics. We submit our results to the ETH3D two-view stereo benchmark to evaluate the method on real-world stereo images and compare its performance with existing approaches. This submission is part of our academic research. |
| Programming language(s) | Python with CUDA (PyTorch) |
| Hardware | NVIDIA GeForce RTX 4090 (24 GB VRAM), single GPU |
| Submission creation date | 9 Sep, 2026 |
| Last edited | 9 Sep, 2026 |
High-res multi-view results
| Info | all | high-res multi-view | indoor | outdoor | courty. | delive. | electro | facade | kicker | meadow | office | pipes | playgr. | relief | relief. | terrace | terrai. |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No results yet. | |||||||||||||||||
Low-res many-view results
| Info | all | low-res many-view | indoor | outdoor | lakeside | sand box | storage room | storage room 2 | tunnel |
|---|---|---|---|---|---|---|---|---|---|
| No results yet. | |||||||||
