Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction
Daeyun Shin, Charless Fowlkes, Derek Hoiem
In CVPR, 2018   [pdf]   [supplementary material]   [poster]   [code]





Citing 
@inproceedings{shin2018pixels,
  title = {Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction},
  author = {Shin, Daeyun and Fowlkes, Charless and Hoiem, Derek},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
}


Please also see our new ICCV 2019 paper on scene reconstruction:

3D Scene Reconstruction with Multi-layer Depth and Epipolar Transformers