iccv-2017

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

Intrinsic3D - High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting (ICCV 2017)

RMPE: Regional Multi-person Pose Estimation, forked from Caffe. Research purpose only.

Soft Proposal Networks for Weakly Supervised Object Localization, in ICCV 2017

Code for "Unsupervised Adaptation for Deep Stereo" - ICCV17

Chainer Implementation of Mask R-CNN. (Training code to reproduce the original result is available.)

this repo attemps to reproduce Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks(CycleGAN) use gluon reimplementation

this repo attemps to reproduce DSOD: Learning Deeply Supervised Object Detectors from Scratch use gluon reimplementation

This is an un-official re-implementation of the work Sketching with Style presented at ICCV 2017 by Prof. John Collomosse's Group and Adobe.

Download papers and other supplementals from ICCV2017/CVPR2017 in fast and wisely-organized way

近期要读的2017年顶会的几篇行为识别论文