Virtual Multi-view Fusion

Virtual Multi-view Fusion for 3D Semantic Segmentation

Paper Short Video Long Video

Abstract

Input mesh

Output labeled mesh

Semantic segmentation of 3D meshes is an important problem for 3D scene understanding. In this paper we revisit the classic multiview representation of 3D meshes and study several techniques that make them effective for 3D semantic segmentation of meshes. Given a 3D mesh reconstructed from RGBD sensors, our method effectively chooses different virtual views of the 3D mesh and renders multiple 2D channels for training an effective 2D semantic segmentation model. Features from multiple per view predictions are finally fused on 3D mesh vertices to predict mesh semantic segmentation labels. Using the large scale indoor 3D semantic segmentation benchmark of ScanNet, we show that our virtual views enable more effective training of 2D semantic segmentation networks than previous multiview approaches. When the 2D per pixel predictions are aggregated on 3D surfaces, our virtual multiview fusion method is able to achieve significantly better 3D semantic segmentation results compared to all prior multiview approaches and recent 3D convolution approaches.

Method

Results

Interactive meshes segmented by our method

NYU 20 category legend

More results on Scannet dataset

NYU 20 category legend

Citation

For attribution in academic contexts, please cite this work as

  1. @inproceedings{KunduECCV2020VirtualMVFusion,
      title = {Virtual Multi-view Fusion for 3D Semantic Segmentation},
      author = {Kundu, Abhijit and Yin, Xiaoqi and Fathi, Alireza and Ross, David and Brewington, Brian and Funkhouser, Thomas and Pantofaru, Caroline},
      booktitle = {ECCV},
      year = {2020},
      doi = {10.1007/978-3-030-58586-0_31},
      url = {https://doi.org/10.1007/978-3-030-58586-0_31},
      isbn = {978-3-030-58586-0},
    }