Results for MonStereo
Submission data
| Full name | Monocular and Stereo Matching Network(MonSter) |
| Description | This method is a pure deep learning stereo matching network based on MonSter. It uses a Vision Transformer (ViT) backbone and iterative geometric reasoning to produce high-quality disparity maps. The input consists of stereo pairs, and the output is a subpixel-accurate disparity map. We apply this method to ETH3D two-view stereo benchmark without additional post-processing or depth refinement. |
| Parameters | * Vision Transformer: vitl
* Correlation levels: 2 * Correlation radius: 4 * Number of GRU layers: 3 * Max disparity: 192 * Iterations: 32 * Mixed precision: enabled |
| Programming language(s) | Python + PyTorch with CUDA |
| Hardware | Intel Core i7-10700, RTX 3060 6GB, 32 GB RAM |
| Submission creation date | 7 Jul, 2025 |
| Last edited | 7 Jul, 2025 |
High-res multi-view results
| Info | all | high-res multi-view | indoor | outdoor | botani. | boulde. | bridge | door | exhibi. | lectur. | living. | lounge | observ. | old co. | statue | terrac. |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 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. | |||||||||
