Papers › End-to-end Learning for Joint Depth and Image Reconstruction from Diffracted Rotation
End-to-end Learning for Joint Depth and Image Reconstruction from Diffracted Rotation
Mazen Mel, Muhammad Siddiqui, Pietro Zanuttigh
Monocular depth estimation is still an open challenge due to the ill-posed nature of the problem at hand. Deep learning based techniques have been extensively studied and proved capable of producing acceptable depth estimation accuracy even if the lack of meaningful and robust depth cues within single RGB input images severally limits their performance. Coded aperture-based methods using phase and amplitude masks encode strong depth cues within 2D images by means of depth-dependent Point Spread Functions (PSFs) at the price of a reduced image quality. In this paper, we propose a novel end-to-end learning approach for depth from diffracted rotation. A phase mask that produces a Rotating Point Spread Function (RPSF) as a function of defocus is jointly optimized with the weights of a depth estimation neural network. To this aim, we introduce a differentiable physical model of the aperture mask and exploit an accurate simulation of the camera imaging pipeline. Our approach requires a significantly less complex model and less training data, yet it is superior to existing methods in the task of monocular depth estimation on indoor benchmarks. In addition, we address the problem of image degradation by incorporating a non-blind and non-uniform image deblurring module to recover the sharp all-in-focus image from its RPSF-blurred counterpart.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Monocular Depth Estimation | SUN-RGBD | RPSF | Delta < 1.25 | 0.937 | #1 of 3 | Archive leaderboard | report |
| Monocular Depth Estimation | SUN-RGBD | RPSF | Delta < 1.25^2 | 0.981 | #1 of 3 | Archive leaderboard | report |
| Monocular Depth Estimation | SUN-RGBD | RPSF | Delta < 1.25^3 | 0.992 | #1 of 3 | Archive leaderboard | report |
| Monocular Depth Estimation | SUN-RGBD | RPSF | RMSE | 0.335 | #1 of 3 | Archive leaderboard | report |
| Monocular Depth Estimation | SUN-RGBD | RPSF | absolute relative error | 0.114 | #1 of 3 | Archive leaderboard | report |
| Monocular Depth Estimation | SUN-RGBD | RPSF | log 10 | 0.034 | #1 of 3 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections