Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation
This work addresses the problem of efficient and accurate motion estimation in computer vision, offering a method that balances parameter reduction and performance gains, though it is incremental in nature.
The paper tackles optical flow and occlusion estimation by proposing an iterative residual refinement scheme that reduces parameters and improves accuracy, achieving state-of-the-art results on multiple datasets.
Deep learning approaches to optical flow estimation have seen rapid progress over the recent years. One common trait of many networks is that they refine an initial flow estimate either through multiple stages or across the levels of a coarse-to-fine representation. While leading to more accurate results, the downside of this is an increased number of parameters. Taking inspiration from both classical energy minimization approaches as well as residual networks, we propose an iterative residual refinement (IRR) scheme based on weight sharing that can be combined with several backbone networks. It reduces the number of parameters, improves the accuracy, or even achieves both. Moreover, we show that integrating occlusion prediction and bi-directional flow estimation into our IRR scheme can further boost the accuracy. Our full network achieves state-of-the-art results for both optical flow and occlusion estimation across several standard datasets.