Full name | Scalable Stereo Matching Model |
Description | transformer based global stereo matching using stacked multi-resolution vision transformer blocks |
Parameters | ch: 256, ntr:3, num_refine:3, dataset: 1M |
Publication title | S^2M^2 : Scalable Stereo Matching Model for Reliable Depth Estimation |
Publication authors | Junhong Min, Youngpil Jeon, Jimin Kim, Minyong Choi |
Publication venue | ICCV 2025 |
Programming language(s) | Python, Torch |
Hardware | Intel i9-13900K, Nvidia 4090 |
Submission creation date | 3 Mar, 2025 |
Last edited | 27 Jun, 2025 |