Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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.

Martin Kiechle, Simon Hawe, Martin Kleinsteuber• 2013

Related benchmarks

TaskDatasetResultRank
Depth Map Super-ResolutionMiddlebury Venus 8-bit (test)
RMSE0.075
14
Depth Map Super-ResolutionMiddlebury Teddy 8-bit (test)
RMSE0.702
14
Depth Map Super-ResolutionMiddlebury Cones 8-bit (test)
RMSE0.68
14
Depth Map Super-ResolutionMiddlebury Tsukuba v1 (test)
Bad Pixel Rate (delta=1)0.47
13
Depth Map Super-ResolutionMiddlebury Venus v1 (test)
Bad Pixels (%) (delta=1)9
13
Depth Map Super-ResolutionMiddlebury Teddy v1 (test)
Percentage Bad Pixels (delta=1)1.41
13
Depth Map Super-ResolutionMiddlebury Cones v1 (test)
Bad Pixel Rate (delta=1)1.81
13
Depth Map Super-ResolutionMiddlebury Tsukuba 8-bit (test)
RMSE0.255
11
Showing 8 of 8 rows

Other info

Code

Follow for update