3DSF-MixNet: Mixer-Based Symmetric Scene Flow Estimation From 3D Point Clouds
Shuaijun Wang, Rui Tao Gao, Ruihua Han, Qi Hao · IEEE Robotics and Automation Letters · 2023
The scene flow estimation aims at accurately achieving the motion of 3D points, imposing challenges like mis-registration, object occlusions, and non-uniform upsampling. This paper introduces a scene flow estimation framework featuring a unified scene flow estimator, a symmetric cost volume approach, and a geometric/semantic feature based upsampling strategy. The novelty of this work is threefold: (1) developing a novel progressive framework which integrates the cost volume module and scene flow estimator, enhancing scene flow estimation; (2) developing a symmetric inter-frame correlation feature extraction method through cost volume estimation using MLP-Mixer operations; (3) developing an upsampling strategy based on both the semantic and geometric feature similarities between sparse and dense samples. Experimental results show that our method outperforms state-of-the-art baseline methods, especially in scenarios involving challenging conditions, the improvements of our method achieving at most$\text{0.109}\, {\text {m}}/0.089\,m/0.091\,m$in EPE3D,$54.23\%/53.67\%/74.1\%$in AS,$32.75\%/21.87\%/40.25\%$in AR, and$70.98\%/58.06\%/43.56\%$in outliers, when tested on FlyingThings3D ($\mathrm{FT3D_{S}}$,$\mathrm{FT3D_{H}}$) and$\mathrm{KITTI_{H}}$datasets, respectively.