Zhuoran Deng

Bio: Zhuoran Deng is an academic researcher from Beijing University of Chemical Technology. The author has contributed to research in topics: Computer science & Pattern recognition (psychology). The author has co-authored 1 publications.

Fast 3D face reconstruction from a single image combining attention mechanism and graph convolutional network

Abstract: Abstract In recent years, researchers have made significant contributions to 3D face reconstruction with the rapid development of deep learning. However, learning-based methods often suffer from time and memory consumption. Simply removing network layers hardly solves the problem. In this study, we propose a solution that achieves fast and robust 3D face reconstruction from a single image without the need for accurate 3D data for training. In terms of increasing speed, we use a lightweight network as a facial feature extractor. As a result, our method reduces the reliance on graphics processing units, allowing fast inference on central processing units alone. To maintain robustness, we combine an attention mechanism and a graph convolutional network in parameter regression to concentrate on facial details. We experiment with different combinations of three loss functions to obtain the best results. In comparative experiments, we evaluate the performance of the proposed method and state-of-the-art methods on 3D face reconstruction and sparse face alignment, respectively. Experiments on a variety of datasets validate the effectiveness of our method.

A high-throughput catalyst synthesis system for Ag-based catalysts.

Abstract: Ag-based catalysts have been used in many practical reactions, such as p-nitrophenol reduction, due to the advantages of low cost and excellent activity. In order to facilitate the development of Ag-based catalysts, it may be helpful to use automated equipment for experiments. In this study, a system for the high-throughput synthesis of Ag-based catalysts was developed based on a facile impregnation method. Notably, the system automates the batch synthesis of Ag-based catalysts by setting the catalyst formulation in a dedicated software. Moreover, the software used employs the ant colony algorithm to optimize the synthesis path and improve the synthesis efficiency. The catalysts obtained from the high-throughput system are found to be similar to the manually prepared samples based on comparison of characterization results. In addition, experiments also reveal that this high-throughput system is capable of achieving high-throughput synthesis of Ag-based catalysts at the gram level. The synthesis of Pt-Ag bimetallic catalysts shows that this high-throughput system can be effectively used for exploratory experiments. This work paves the way for a high-throughput technique to synthesize Ag-based catalysts in a short period of time, which could be extended to the preparation of other catalyst systems. Moreover, the high-throughput synthesis system of Ag-based catalysts provides a feasible prerequisite for subsequent high-throughput characterization, which is a significant advancement in the development of industrial catalysts.

Structures and structural evolution of MN (M = Pt, Ag, Au, N=2-20) from combined revised particle swarm optimization and density function theory

Abstract: Structure is the key to understanding the properties of metal nanoclusters. Finding a globally optimal structure on an extremely complex potential energy surface is a great challenge for theoretica...

Interactive Face Video Coding: A Generative Compression Framework

Abstract: In this paper, we propose a novel framework for Interactive Face Video Coding (IFVC), which allows humans to interact with the intrinsic visual representations instead of the signals. The proposed solution enjoys several distinct advantages, including ultra-compact representation, low delay interaction, and vivid expression and headpose animation. In particular, we propose the Internal Dimension Increase (IDI) based representation, greatly enhancing the fidelity and flexibility in rendering the appearance while maintaining reasonable representation cost. By leveraging strong statistical regularities, the visual signals can be effectively projected into controllable semantics in the three dimensional space (e.g., mouth motion, eye blinking, head rotation and head translation), which are compressed and transmitted. The editable bitstream, which naturally supports the interactivity at the semantic level, can synthesize the face frames via the strong inference ability of the deep generative model. Experimental results have demonstrated the performance superiority and application prospects of our proposed IFVC scheme. In particular, the proposed scheme not only outperforms the state-of-the-art video coding standard Versatile Video Coding (VVC) and the latest generative compression schemes in terms of rate-distortion performance for face videos, but also enables the interactive coding without introducing additional manipulation processes. Furthermore, the proposed framework is expected to shed lights on the future design of the digital human communication in the metaverse.

Heterogeneous differential evolution particle swarm optimization with local search

Abstract: Abstract To develop a high performance and widely applicable particle swarm optimization (PSO) algorithm, a heterogeneous differential evolution particle swarm optimization (HeDE-PSO) is proposed in this study. HeDE-PSO adopts two differential evolution (DE) mutants to construct different characteristics of learning exemplars for PSO, one DE mutant is for enhancing exploration and the other is for enhance exploitation. To further improve search accuracy in the late stage of optimization, the BFGS (Broyden–Fletcher–Goldfarb–Shanno) local search is employed. To assess the performance of HeDE-PSO, it is tested on the CEC2017 test suite and the industrial refrigeration system design problem. The test results are compared with seven recent PSO algorithms, JADE (adaptive differential evolution with optional external archive) and four meta-heuristics. The comparison results show that with two DE mutants to construct learning exemplars, HeDE-PSO can balance exploration and exploitation and obtains strong adaptability on different kinds of optimization problems. On 10-dimensional functions and 30-dimensional functions, HeDE-PSO is only outperformed by the most competitive PSO algorithm on seven and six functions, respectively. HeDE-PSO obtains the best performance on sixteen 10-dimensional functions and seventeen-30 dimensional functions. Moreover, HeDE-PSO outperforms other compared PSO algorithms on the industrial refrigeration system design problem.