iccv-2017 topic

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

ZhouYanzhao

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

NVlabs

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

una-dinosauria

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

MVIG-SJTU

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

wkentaro

Code for "Unsupervised Adaptation for Deep Stereo" - ICCV17

CVLAB-Unibo

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

leocvml