[ECCV 2020] Flow-edge Guided Video Completion

[CVPR 2020] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

[ECCV 2020] NAS-DIP: Learning Deep Image Prior with Neural Architecture Search

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.

NEC-Drone-Dataset

[CVPR 2019] CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

[CVPR 2020] Learning to See Through Obstructions

[ICCV 2019] Guided Image-to-Image Translation with Bi-Directional Feature Transformation

[PAMI 2020] Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation

[ECCV 2018] DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency

source code to ICLR'19, 'A Closer Look at Few-shot Classification'

Multi-view Wire Art

[BMVC 2018] iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection

DeepMVS: Learning Multi-View Stereopsis

TensorFlow tutorials and best practices.

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (CVPR 2017)

gvnn: Geometric Vision with Neural Networks

Style guides for Google-originated open-source projects

A Comparative Study for Single Image Blind Deblurring (CVPR 2016)

Detecting Migrating Birds at Night (CVPR 2016)

Weakly Supervised Object Localization with Progressive Domain Adaptation (CVPR 2016)

The C++ Core Guidelines are a set of tried-and-true guidelines, rules, and best practices about coding in C++

Hierarchical Convolutional Features for Visual Tracking (ICCV 2015)

Torch implementation of neural style algorithm

Single Image Super-Resolution from Transformed Self-Exemplars (CVPR 2015)

R-CNN: Regions with Convolutional Neural Network Features

Fast R-CNN