CVPR 2017

Learning from Simulated and Unsupervised Images through Adversarial Training

CVPR 2017 tensorflow/models

With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations.

GAZE ESTIMATION HAND POSE ESTIMATION IMAGE-TO-IMAGE TRANSLATION

Full Resolution Image Compression with Recurrent Neural Networks

CVPR 2017 tensorflow/models

As far as we know, this is the first neural network architecture that is able to outperform JPEG at image compression across most bitrates on the rate-distortion curve on the Kodak dataset images, with and without the aid of entropy coding.

IMAGE COMPRESSION

Aggregated Residual Transformations for Deep Neural Networks

CVPR 2017 facebookresearch/detectron

Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set.

IMAGE CLASSIFICATION

Densely Connected Convolutional Networks

CVPR 2017 liuzhuang13/DenseNet

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output.

IMAGE CLASSIFICATION OBJECT RECOGNITION

EAST: An Efficient and Accurate Scene Text Detector

CVPR 2017 argman/EAST

Previous approaches for scene text detection have already achieved promising performances across various benchmarks.

CURVED TEXT DETECTION

Fully Convolutional Instance-aware Semantic Segmentation

CVPR 2017 msracver/FCIS

It inherits all the merits of FCNs for semantic segmentation and instance mask proposal.

SEMANTIC SEGMENTATION

Deep Feature Flow for Video Recognition

CVPR 2017 msracver/Deep-Feature-Flow

Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable.

VIDEO RECOGNITION

Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis

CVPR 2017 DmitryUlyanov/texture_nets

The recent work of Gatys et al., who characterized the style of an image by the statistics of convolutional neural network filters, ignited a renewed interest in the texture generation and image stylization problems.

IMAGE GENERATION IMAGE STYLIZATION TEXTURE SYNTHESIS

Unsupervised Learning of Depth and Ego-Motion from Video

CVPR 2017 tinghuiz/SfMLearner

We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences.

DEPTH AND CAMERA MOTION MOTION ESTIMATION POSE ESTIMATION