Joint Image and Depth Estimation with Mask-Based Lensless Cameras
This work addresses depth recovery challenges in lensless cameras for applications like thin or flexible imaging devices, but it is incremental as it builds on existing methods to handle more complex scenes.
The paper tackles the problem of depth estimation in mask-based lensless cameras, which struggle with scenes having large depth variations, by proposing an alternating gradient descent algorithm that jointly estimates continuous depth maps and light distribution. The result shows improved robustness for natural scenes with a wide depth range, supported by simulation and experimental results from a prototype camera.
Mask-based lensless cameras replace the lens of a conventional camera with a custom mask. These cameras can potentially be very thin and even flexible. Recently, it has been demonstrated that such mask-based cameras can recover light intensity and depth information of a scene. Existing depth recovery algorithms either assume that the scene consists of a small number of depth planes or solve a sparse recovery problem over a large 3D volume. Both these approaches fail to recover the scenes with large depth variations. In this paper, we propose a new approach for depth estimation based on an alternating gradient descent algorithm that jointly estimates a continuous depth map and light distribution of the unknown scene from its lensless measurements. We present simulation results on image and depth reconstruction for a variety of 3D test scenes. A comparison between the proposed algorithm and other method shows that our algorithm is more robust for natural scenes with a large range of depths. We built a prototype lensless camera and present experimental results for reconstruction of intensity and depth maps of different real objects.