Sdf-GAN: Semi-supervised Depth Fusion with Multi-scale Adversarial Networks
This addresses the challenge of depth fusion for computer vision applications, but it is incremental as it builds on existing adversarial and semi-supervised techniques.
The paper tackles the problem of refining raw disparity maps from different algorithms by introducing a method that fuses them with supplementary information using multi-scale adversarial networks, achieving superior results on synthetic and real datasets compared to recent algorithms.
Refining raw disparity maps from different algorithms to exploit their complementary advantages is still challenging. Uncertainty estimation and complex disparity relationships among pixels limit the accuracy and robustness of existing methods and there is no standard method for fusion of different kinds of depth data. In this paper, we introduce a new method to fuse disparity maps from different sources, while incorporating supplementary information (intensity, gradient, etc.) into a refiner network to better refine raw disparity inputs. A discriminator network classifies disparities at different receptive fields and scales. Assuming a Markov Random Field for the refined disparity map produces better estimates of the true disparity distribution. Both fully supervised and semi-supervised versions of the algorithm are proposed. The approach includes a more robust loss function to inpaint invalid disparity values and requires much less labeled data to train in the semi-supervised learning mode. The algorithm can be generalized to fuse depths from different kinds of depth sources. Experiments explored different fusion opportunities: stereo-monocular fusion, stereo-ToF fusion and stereo-stereo fusion. The experiments show the superiority of the proposed algorithm compared with the most recent algorithms on public synthetic datasets (Scene Flow, SYNTH3, our synthetic garden dataset) and real datasets (Kitti2015 dataset and Trimbot2020 Garden dataset).