实验室简介
编码摄像实验室隶属于清华大学自动化系,我们通过联合设计光学、传感器、信号处理和计算机视觉领域的新方法,致力于解决成像和视觉方面的难题,例如散射场景成像,图像增强,视觉目标检测,场景深度估计,物体姿态估计,生物特征识别,生命体征信号检测等。这个新兴的研究领域被称为编码摄像,我们的研究不仅包括基础理论、算法和平台系统,还聚焦于网络多媒体、工业视觉、智能医疗、智能交通等实际应用场景。 点击了解更多>>
亮点文章
Yi Li, Gu Wang, Xiangyang Ji, Yu Xiang, Dieter Fox . In European Conference on Computer Vision (ECCV), 2018 (oral).Project Page

In this work, we propose DeepIM, a new refinement technique based on a deep neural network for iterative 6D pose matching. Given an initial 6D pose estimation of an object in a test image, DeepIM predicts a relative SE(3) trans- formation that matches a rendered view of the object against the observed image.

Yi Li ; Haozhi Qi ; Jifeng Dai ; Xiangyang Ji ; Yichen Wei. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2017.Project Page

We present the first fully convolutional end-to-end solution for instance-aware semantic segmentation task. By the introduction of position-senstive inside/outside score maps, the underlying convolutional representation is fully shared between the two sub-tasks, as well as between all regions of interest.

Zhigang Li ; Gu Wang ; Xiangyang Ji. IEEE/CVF International Conference on Computer Vision (ICCV),2019.Project Page

We propose a novel 6-DoF pose estimation approach: Coordinates-based Disentangled Pose Network (CDPN), which disentangles the pose to predict rotation and translation separately to achieve highly accurate and robust pose estimation.

Di Yan ; Henrique Morimitsu ; Shan Gao ; Xiangyang Ji. IEEE/CVF International Conference on Computer Vision (ICCV),2019.Project Page

We propose a novel and specially designed method for piecewise dense monocular depth estimation in dynamic scenes. We utilize spatial relations between neighboring superpixels to solve the inherent relative scale ambiguity (RSA) problem and smooth the depth map.

Pengfei Wan ; Jiexiang Tan ; Xiaocong Lian ; Xiangyang Ji. IEEE Transactions on Computational Imaging ,2019.Project Page

We present a novel image acquisition framework capable of reconstructing high bit-depth images using an array of low bit-depth scalar quantizers. Through the collaborative design of the sampling end and the reconstruction end, we achieve high-quality image acquisition and reconstruction.

用户登录

用户注册