A Joint Intensity and Depth Co-Sparse Analysis Model for Depth Map Super-Resolution
About
High-resolution depth maps can be inferred from low-resolution depth measurements and an additional high-resolution intensity image of the same scene. To that end, we introduce a bimodal co-sparse analysis model, which is able to capture the interdependency of registered intensity and depth information. This model is based on the assumption that the co-supports of corresponding bimodal image structures are aligned when computed by a suitable pair of analysis operators. No analytic form of such operators exist and we propose a method for learning them from a set of registered training signals. This learning process is done offline and returns a bimodal analysis operator that is universally applicable to natural scenes. We use this to exploit the bimodal co-sparse analysis model as a prior for solving inverse problems, which leads to an efficient algorithm for depth map super-resolution.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Depth Map Super-Resolution | Middlebury Venus 8-bit (test) | RMSE0.075 | 14 | |
| Depth Map Super-Resolution | Middlebury Teddy 8-bit (test) | RMSE0.702 | 14 | |
| Depth Map Super-Resolution | Middlebury Cones 8-bit (test) | RMSE0.68 | 14 | |
| Depth Map Super-Resolution | Middlebury Tsukuba v1 (test) | Bad Pixel Rate (delta=1)0.47 | 13 | |
| Depth Map Super-Resolution | Middlebury Venus v1 (test) | Bad Pixels (%) (delta=1)9 | 13 | |
| Depth Map Super-Resolution | Middlebury Teddy v1 (test) | Percentage Bad Pixels (delta=1)1.41 | 13 | |
| Depth Map Super-Resolution | Middlebury Cones v1 (test) | Bad Pixel Rate (delta=1)1.81 | 13 | |
| Depth Map Super-Resolution | Middlebury Tsukuba 8-bit (test) | RMSE0.255 | 11 |