2. VcnVolumetric Correspondence Networks for Optical Flow, NeurIPS 2019.
3. viser-releaseViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction. NeurIPS 2021.
4. rigidmaskCode for "Learning to Segment Rigid Motions from Two Frames". CVPR 2021.
5. expansionUpgrading Optical Flow to 3D Scene Flow through Optical Expansion, CVPR 2020 (Oral).