Light your way in Deep Learning with Torch 🔦

gvnn: Geometric Vision with Neural Networks

ICRA 2018 "Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image" (Torch Implementation)

Volumetric CNN for feature extraction and object classification on 3D data.

Code for "Multi-Context Attention for Human Pose Estimation " (CVPR 2017)

Code release for "Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction"

[CVPR 2018] Cross-View Image Synthesis using Conditional GANs, [CVIU 2019] Cross-view image synthesis using geometry-guided conditional GANs

Searching the limits of how much Neural Networks can extract motion information given optical flow or sequence images