INS-Conv: Incremental Sparse Convolution for Online 3D Segmentation

CVPR 2022  ·  Leyao Liu, Tian Zheng, Yun-Jou Lin, Kai Ni, Lu Fang ·

We propose INS-Conv, an INcremental Sparse Convolutional network which enables online accurate 3D semantic and instance segmentation. Benefiting from the incremental nature of RGB-D reconstruction, we only need to update the residuals between the reconstructed scenes of consecutive frames, which are usually sparse. For layer design, we define novel residual propagation rules for sparse convolution operations, achieving close approximation to standard sparse convolution. For network architecture, an uncertainty term is proposed to adaptively select which residual to update, further improving the inference accuracy and efficiency. Based on INS-Conv, an online joint 3D semantic and instance segmentation pipeline is proposed, reaching an inference speed of 15 FPS on GPU and 10 FPS on CPU. Experiments on ScanNetv2 and SceneNN datasets show that the accuracy of our method surpasses previous online methods by a large margin, and is on par with state-of-the-art offline methods. A live demo on portable devices further shows the superior performance of INS-Conv.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.