PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation
This work improves scene flow estimation for applications like autonomous driving by offering a more efficient deep learning method, though it is incremental as it builds on existing CNN approaches.
The paper tackles scene flow estimation from stereo image sequences by proposing PWOC-3D, a compact CNN architecture that addresses large motion and occlusions, achieving competitive results on benchmarks like KITTI and FlyingThings3D, with 48 times fewer parameters than the top method on KITTI.
In the last few years, convolutional neural networks (CNNs) have demonstrated increasing success at learning many computer vision tasks including dense estimation problems such as optical flow and stereo matching. However, the joint prediction of these tasks, called scene flow, has traditionally been tackled using slow classical methods based on primitive assumptions which fail to generalize. The work presented in this paper overcomes these drawbacks efficiently (in terms of speed and accuracy) by proposing PWOC-3D, a compact CNN architecture to predict scene flow from stereo image sequences in an end-to-end supervised setting. Further, large motion and occlusions are well-known problems in scene flow estimation. PWOC-3D employs specialized design decisions to explicitly model these challenges. In this regard, we propose a novel self-supervised strategy to predict occlusions from images (learned without any labeled occlusion data). Leveraging several such constructs, our network achieves competitive results on the KITTI benchmark and the challenging FlyingThings3D dataset. Especially on KITTI, PWOC-3D achieves the second place among end-to-end deep learning methods with 48 times fewer parameters than the top-performing method.