CMU-Flownet: Exploring Point Cloud Scene Flow Estimation in Occluded Scenario
This addresses a critical challenge in autonomous driving and robotics by improving scene flow estimation under occlusions, though it appears incremental as it builds on existing network architectures with enhanced modules.
The paper tackles the problem of point cloud scene flow estimation in occluded scenarios, where occlusions hinder frame alignment in LiDAR data, and introduces CMU-Flownet, which achieves state-of-the-art performance on occluded Flyingthings3D and KITTY datasets, surpassing previous methods across most metrics.
Occlusions hinder point cloud frame alignment in LiDAR data, a challenge inadequately addressed by scene flow models tested mainly on occlusion-free datasets. Attempts to integrate occlusion handling within networks often suffer accuracy issues due to two main limitations: a) the inadequate use of occlusion information, often merging it with flow estimation without an effective integration strategy, and b) reliance on distance-weighted upsampling that falls short in correcting occlusion-related errors. To address these challenges, we introduce the Correlation Matrix Upsampling Flownet (CMU-Flownet), incorporating an occlusion estimation module within its cost volume layer, alongside an Occlusion-aware Cost Volume (OCV) mechanism. Specifically, we propose an enhanced upsampling approach that expands the sensory field of the sampling process which integrates a Correlation Matrix designed to evaluate point-level similarity. Meanwhile, our model robustly integrates occlusion data within the context of scene flow, deploying this information strategically during the refinement phase of the flow estimation. The efficacy of this approach is demonstrated through subsequent experimental validation. Empirical assessments reveal that CMU-Flownet establishes state-of-the-art performance within the realms of occluded Flyingthings3D and KITTY datasets, surpassing previous methodologies across a majority of evaluated metrics.