Xiaoping Liu

Bio: Xiaoping Liu is an academic researcher from Hefei University of Technology. The author has contributed to research in topics: Structure from motion & 3D reconstruction. The author has an hindex of 6, co-authored 44 publications receiving 177 citations. Previous affiliations of Xiaoping Liu include Peking University.

Deep Reconstruction of Least Significant Bits for Bit-Depth Expansion

Abstract: Bit-depth expansion (BDE) is important for displaying a low bit-depth image in a high bit-depth monitor. Current BDE algorithms often utilize traditional methods to fill the missing least significant bits and suffer from multiple kinds of perceivable artifacts. In this paper, we present a deep residual network-based method for BDE. Based on the different properties of flat and non-flat areas, two channels are proposed to reconstruct these two kinds of areas, respectively. Moreover, a simple yet efficient local adaptive adjustment preprocessing is presented in the flat-area-channel. By combining the benefits of both the traditional debanding strategy and network-based reconstruction, the proposed method can further promote the subjective quality of the flat area. Experimental results on several image sets demonstrate that the proposed BDE network can obtain favorable visual quality and decent quantitative performance.

Robust bundle adjustment for large-scale structure from motion

Abstract: Bundle adjustment (BA) is the problem of refining a visual reconstruction to produce jointly optimal 3D structure and viewing parameter (camera pose and or calibration) estimates, and it is almost always used as the last step of feature-based 3D reconstruction algorithm. Generally, the result of Structure from Motion (SFM) mainly relies on the quality of BA. The problem of BA is often formulated as a nonlinear least squares problem, where the data arises from keypoints matching. For 3D reconstruction, mismatched keypoints may cause serious problems, even a single mismatch will affect the entire reconstruction. Therefore, to further impove the robustness of BA algorithm is very necessary. In this paper, we propose a robust Bundle Adjustment (RBA) algorithm to optimize the initial 3D point-clouds and camera parameters which are produced by the SFM system. In the proposed RBA algorithm, we firstly use the Huber loss function to potentially down-weight outliers. Secondly, we split a large-scale bundle adjustment problem into some small ones by making use of the sparsity between 3D points and the cameras for reducing the requirements of memory. Thirdly, according to the inherent property of the matrix after it spare decompose, we use a fast matrix factorization algorithm to solve the normal equation to avoid calculating the inverse of large-scale matrix. Finally, we evaluate the proposed RBA method and compare it with the state-of-the-art methods on the synthetic dataset, BAL benchmark and real image datasets, respectively. Experimental results show that the proposed RBA method clearly outperforms the state-of-the-art methods on both computational cost and precision.

Differently implicational universal triple I method of (1, 2, 2) type

Abstract: As a generalization of the triple I method, differently implicational universal triple I method of (1, 2, 2) type (universal triple I method for short) is investigated. First, the concepts of residual operators and strongly residual operators are given, and then related conclusions of residual pairs are provided. Second, the related universal triple I solutions (including FMP-solutions, FMT-solutions and so on) are strictly defined by the infimum, where such solutions are divided into two parts respectively corresponding to the minimum and infimum. Then, we put emphasis on the FMP-solutions, in which the unified forms of FMP-solutions w.r.t. strongly residual operators and a new idea for getting FMP-solutions w.r.t. infimum are achieved. Third, as a result of analyzing the logic basis of a sort of CRI (Compositional Rule of Inference) method, it is found that their CRI solutions can be regarded as special cases of FMP-solutions. Lastly, the response functions of fuzzy systems via universal triple I method are discussed, which demonstrates that the universal triple I method can provide bigger choosing space and get better fuzzy controllers by contrast with the triple I method and CRI method.

Joint 3D Reconstruction and Object Tracking for Traffic Video Analysis Under IoV Environment

Abstract: Benefits from artificial intelligence and the Internet of Vehicles (IoV), Management of modern transportation have great progress, especially in urban areas. However, traditional traffic video analysis and visualization are usually conducted in offsite and textural environments, i.e., text and number, which do not promote user’s sensorial perception and interaction. Thus, the problem that how to use modern novel techniques to analyze traffic video for improving intelligent transportation is so emergency. In this paper, we introduce a joint 3D reconstruction and object tracking approach to traffic video analysis under the IoV environment, which is an integrative framework and consists of 3D reconstruction, object detection, and visual tracking. The 3D reconstruction system is connected to the Internet of Vehicles and integrated into the system to retrieve image data for recovering the 3D model of vehicles, and then, visualizing vehicle trajectories in real-time by augmented reality. And the system can also locate the vehicle’s position in real-time. The experiments in both laboratory and practice show great feedback, which will effectively contribute to intelligent transportation.

Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Abstract: Recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) input image is challenging due to missing details in under-/over-exposed regions caused by quantization and saturation of camera sensors. In contrast to existing learning-based methods, our core idea is to incorporate the domain knowledge of the LDR image formation pipeline into our model. We model the HDR-to-LDR image formation pipeline as the (1) dynamic range clipping, (2) non-linear mapping from a camera response function, and (3) quantization. We then propose to learn three specialized CNNs to reverse these steps. By decomposing the problem into specific sub-tasks, we impose effective physical constraints to facilitate the training of individual sub-networks. Finally, we jointly fine-tune the entire model end-to-end to reduce error accumulation. With extensive quantitative and qualitative experiments on diverse image datasets, we demonstrate that the proposed method performs favorably against state-of-the-art single-image HDR reconstruction algorithms.

Screen Content Quality Assessment: Overview, Benchmark, and Beyond

Abstract: Screen content, which is often computer-generated, has many characteristics distinctly different from conventional camera-captured natural scene content. Such characteristic differences impose majo...