Popular GitHub Repositories for Cvpr2018

StarGAN - Official PyTorch Implementation (CVPR 2018)

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)

Gibson Environments: Real-World Perception for Embodied Agents

Unsupervised Feature Learning via Non-parametric Instance Discrimination

Inference Code for Polygon-RNN++ (CVPR 2018)

CVPR 论文收集，包含但不限于2022、2021、2020、2019、2018、2017文章

This repository contains the source codes for the paper "AtlasNet: A Papier-Maché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity) from a low-resolution point cloud, or from an image.

365 Days Computer Vision Learning Linkedin Post

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)

Optical Flow Prediction with TensorFlow. Implements "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume," by Deqing Sun et al. (CVPR 2018)

Densely Connected Pyramid Dehazing Network (CVPR'2018)

PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image

Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018

This is a re-implementation of Siamese-RPN with pytorch, which is CVPR2018 spotlight.

Paper: CVPR2018, Learning Rich Features for Image Manipulation Detection

Geometry-Aware Learning of Maps for Camera Localization (CVPR2018)

Unofficial tensorflow implemention of "Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR 2018) " model https://maybeshewill-cv.github.io/attentive-gan-derainnet/

This is a pytorch re-implementation of Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition

Density-aware Single Image De-raining using a Multi-stream Dense Network (CVPR 2018)

Contains implementation of Guided Attention Inference Network (GAIN) presented in Tell Me Where to Look(CVPR 2018). This repository aims to apply GAIN on fcn8 architecture used for segmentation.