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.

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.

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.

We propose an optimized block-floating-point (BFP) arithmetic for efficient inference of deep neural networks. The proposed reconfigurable accelerator with three parallelism dimensions, ping-pong off-chip DDR3 memory access, and an optimized on-chip buffer group is implemented on the Xilinx VC709 evaluation board.

We present an algorithm based on the Optimism in the Face of Uncertainty (OFU) principle which is able to learn Reinforcement Learning (RL) modeled by Markov decision process (MDP) with finite state-action space efficiently.

We present a rate control algorithm in which the frame base QP is determined with not only the coding complexity history but also the complexity changes and the data dependencies between the current and the near future pictures by exploring lookahead. Moreover, the quantization scale is introduced to the threshold specification in slice type decision, which identifies more pictures as B-type properly when increasing QP.

We present a novel deep learning based approach-the Range Scaling Global U-Net (RSGUNet)-for perceptual image enhancement on mobile devices.

We present Dynamic Sampling Convolutional Neural Networks (DSCNN), where the position-specific kernels learn from not only the current position but also multiple sampled neighbour regions.

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.

We present a Multi-perspective Tracking (MPT) framework for intelligent vehicle. An iterative search procedure is proposed to associate detections and tracklets in different perspectives.