Results for SCION-MonSter
Submission data
| Full name | Structurally-compressed Content-preserving Iterative Optimized Network |
| Description | Our research focuses on bridging the performance-efficiency gap in stereo matching by developing SCION-MonSter, a lightweight stereo depth estimation model derived from the state-of-the-art MonSter architecture. |
| Programming language(s) | Python+CUDA |
| Hardware | RTX4090D |
| Website | https://github.com/rayring539/Monsterl-ite |
| Source code or download URL | https://github.com/rayring539/Monsterl-ite.git |
| Submission creation date | 31 Mar, 2026 |
| Last edited | 31 Mar, 2026 |
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. | |||||||||
