In this paper we tackle the problem of stereo image compression, and leverage the fact that the two images have overlapping fields of view to further compress the representations. Our approach leverages state-of-the-art single-image compression autoencoders and enhances the compression with novel parametric skip functions to feed fully differentiable, disparity-warped features at all levels to the encoder/decoder of the second image. Moreover, we model the probabilistic dependence between the image codes using a conditional entropy model. Our experiments show an impressive 30 - 50% reduction in the second image bitrate at low bitrates compared to deep single-image compression, and a 10 - 20% reduction at higher bitrates.
Stereo Image Coding for Machines with Joint Visual Feature Compression
School of Electrical and Information Engineering, Tianjin University（天津大学电气与信息工程学院）；Santa Clara University（圣克拉拉大学）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）
FFCA-Net: Stereo Image Compression via Fast Cascade Alignment of Side Information
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Research Center of Artificial Intelligence, Peng Cheng Laboratory（鹏城实验室人工智能研究中心）
Imperial College London（帝国理工学院）；New York University（纽约大学）；EPFL（洛桑联邦理工学院）
We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distributed source coding problem in information theory. In particular, we consider a pair of stereo images, which have overlapping fields of view, and are captured by a synchronized and calibrated pair of cameras as correlated image sources. In previously proposed methods, the encoder transforms the input image to a latent representation using a deep neural network, and compresses the quantized latent representation lossle…
Isfahan University of Technology（伊斯法罕理工大学）；McMaster University（麦克马斯特大学）；University of Michigan（密歇根大学）
The use of 3D and stereo imaging is rapidly increasing. Compression, transmission, and processing could degrade the quality of stereo images. Quality assessment of such images is different than their 2D counterparts. Metrics that represent 3D perception by human visual system (HVS) are expected to assess stereoscopic quality more accurately. In this paper, inspired by brain sensory/motor fusion process, two stereo images are fused together. Then from every fused image two synthesized images are extracted. Effects of different distortions on statistical distributions of the synthesized images a…
Nankai University（南开大学）；RIKEN（理化学研究所）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）；Hangzhou Dianzi University（杭州电子科技大学）；Nicolaus Copernicus University（哥白尼大学）；NVIDIA Corporation（英伟达公司）
A large number of autonomous driving tasks need high-definition stereo images, which requires a large amount of storage space. Efficiently executing lossless compression has become a practical problem. Commonly, it is hard to make accurate probability estimates for each pixel. To tackle this, we propose L3C-Stereo, a multi-scale lossless compression model consisting of two main modules: the warping module and the probability estimation module. The warping module takes advantage of two view feature maps from the same domain to generate a disparity map, which is used to reconstruct the right vie…
Xidian University（西安电子科技大学）；University of Southern California（南加州大学）
A new stereoscopic image quality assessment database rendered using the 2D-image-plus-depth source, called MCL-3D, is described and the performance benchmarking of several known 2D and 3D image quality metrics using the MCL-3D database is presented in this work. Nine image-plus-depth sources are first selected, and a depth image-based rendering (DIBR) technique is used to render stereoscopic image pairs. Distortions applied to either the texture image or the depth image before stereoscopic image rendering include: Gaussian blur, additive white noise, down-sampling blur, JPEG and JPEG-2000 (JP2…
We propose an algorithm for recovering depth using less than two images. Instead of having both cameras send their entire image to the host computer, the left camera sends its image to the host while the right camera sends only a fraction $ε$ of its image. The key aspect is that the cameras send the information without communicating at all. Hence, the required communication bandwidth is significantly reduced. While standard image compression techniques can reduce the communication bandwidth, this requires additional computational resources on the part of the encoder (camera). We aim at designi…
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
Image feature extraction and matching is a fundamental but computation intensive task in machine vision. This paper proposes a novel FPGA-based embedded system to accelerate feature extraction and matching. It implements SURF feature point detection and BRIEF feature descriptor construction and matching. For binocular stereo vision, feature matching includes both tracking matching and stereo matching, which simultaneously provide feature point correspondences and parallax information. Our system is evaluated on a ZYNQ XC7Z045 FPGA. The result demonstrates that it can process binocular video da…
Imperial College London（帝国理工学院）；Sharif University of Technology（谢里夫理工大学）；New York University（纽约大学）；EPFL（洛桑联邦理工学院）
We present a novel deep neural network (DNN) architecture for compressing an image when a correlated image is available as side information only at the decoder. This problem is known as distributed source coding (DSC) in information theory. In particular, we consider a pair of stereo images, which generally have high correlation with each other due to overlapping fields of view, and assume that one image of the pair is to be compressed and transmitted, while the other image is available only at the decoder. In the proposed architecture, the encoder maps the input image to a latent space, quant…
Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
This paper addresses the problem of correlation estimation in sets of compressed images. We consider a framework where images are represented under the form of linear measurements due to low complexity sensing or security requirements. We assume that the images are correlated through the displacement of visual objects due to motion or viewpoint change and the correlation is effectively represented by optical flow or motion field models. The correlation is estimated in the compressed domain by jointly processing the linear measurements. We first show that the correlated images can be efficientl…
