papers

Publications (22)

cond-mat.mtrl-sci2021

Predicting nanocrystal morphology governed by interfacial strain

Hongwei Liu, Xuan Cheng, Nagarajan Valanoor

The shape dependence for the technologically important nickel oxide (NiO) nanocrystals on (001) strontium titanate substrates is investigated under the generalized Wulff-Kaichew (G…

cs.CV2022

Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions

Xuan Cheng, Tianshu Xie, Xiaomin Wang +4

In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs). Inspired by the diverse ef…

cond-mat.mtrl-sci2021

Super-R BiFeO: Epitaxial stabilization of a low-symmetry phase with giant electromechanical response

Oliver Paull, Changsong Xu, Xuan Cheng +9

Piezoelectrics interconvert mechanical energy and electric charge and are widely used in actuators and sensors. The best performing materials are ferroelectrics at a morphotropic p…

cs.CV2022

Channel Self-Supervision for Online Knowledge Distillation

Shixiao Fan, Xuan Cheng, Xiaomin Wang +5

Recently, researchers have shown an increased interest in the online knowledge distillation. Adopting an one-stage and end-to-end training fashion, online knowledge distillation us…

cs.CV2021

FocusedDropout for Convolutional Neural Network

Tianshu Xie, Minghui Liu, Jiali Deng +3

In convolutional neural network (CNN), dropout cannot work well because dropped information is not entirely obscured in convolutional layers where features are correlated spatially…

cs.CV2022

I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation

Yiwei Ding, Wenjin Deng, Yinglin Zheng +6

In this paper, we present the Intra- and Inter-Human Relation Networks (I^2R-Net) for Multi-Person Pose Estimation. It involves two basic modules. First, the Intra-Human Relation M…

cs.CV2021

Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network

Tianshu Xie, Xuan Cheng, Minghui Liu +3

In this paper, we propose a novel data augmentation strategy named Cut-Thumbnail, that aims to improve the shape bias of the network. We reduce an image to a certain size and repla…

cs.CV2021

Self-supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning

Yuhang Yang, Zilin Ding, Xuan Cheng +2

Traditional self-supervised learning requires CNNs using external pretext tasks (i.e., image- or video-based tasks) to encode high-level semantic visual representations. In this pa…

cs.CV2026

FaceRefiner: High-Fidelity Facial Texture Refinement with Differentiable Rendering-based Style Transfer

Chengyang Li, Baoping Cheng, Yao Cheng +5

Recent facial texture generation methods prefer to use deep networks to synthesize image content and then fill in the UV map, thus generating a compelling full texture from a singl…

cs.CV2026

StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision

Ziyang Chen, Yansong Qu, You Shen +2

Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical research frontier. Contemporary stereo visio…

cs.CV2024

DNPM: A Neural Parametric Model for the Synthesis of Facial Geometric Details

Haitao Cao, Baoping Cheng, Qiran Pu +6

Parametric 3D models have enabled a wide variety of computer vision and graphics tasks, such as modeling human faces, bodies and hands. In 3D face modeling, 3DMM is the most widely…

cs.CV2024

Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation

Renshuai Liu, Bowen Ma, Wei Zhang +5

In human-centric content generation, the pre-trained text-to-image models struggle to produce user-wanted portrait images, which retain the identity of individuals while exhibiting…

cs.CV2023

EMEF: Ensemble Multi-Exposure Image Fusion

Renshuai Liu, Chengyang Li, Haitao Cao +3

Although remarkable progress has been made in recent years, current multi-exposure image fusion (MEF) research is still bounded by the lack of real ground truth, objective evaluati…

cs.CV2024

Learn2Talk: 3D Talking Face Learns from 2D Talking Face

Yixiang Zhuang, Baoping Cheng, Yao Cheng +6

Speech-driven facial animation methods usually contain two main classes, 3D and 2D talking face, both of which attract considerable research attention in recent years. However, to…

cs.CV2022

Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency

Tianshu Xie, Xuan Cheng, Minghui Liu +3

Image resolution that has close relations with accuracy and computational cost plays a pivotal role in network training. In this paper, we observe that the reduced image retains re…

cs.CV2026

CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization

Weilin Chen, Jiahao Rao, Wenhao Wang +3

The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-…

cs.CV2026

TalkingEyes: Pluralistic Speech-Driven 3D Eye Gaze Animation

Yixiang Zhuang, Chunshan Ma, Yao Cheng +3

Although significant progress has been made in the field of speech-driven 3D facial animation recently, the speech-driven animation of an indispensable facial component, eye gaze,…

cs.CV2021

Feature Mining: A Novel Training Strategy for Convolutional Neural Network

Tianshu Xie, Xuan Cheng, Xiaomin Wang +3

In this paper, we propose a novel training strategy for convolutional neural network(CNN) named Feature Mining, that aims to strengthen the network's learning of the local feature.…

cs.CV2021

Go Small and Similar: A Simple Output Decay Brings Better Performance

Xuan Cheng, Tianshu Xie, Xiaomin Wang +3

Regularization and data augmentation methods have been widely used and become increasingly indispensable in deep learning training. Researchers who devote themselves to this have c…

cs.CV2021

Self-supervision of Feature Transformation for Further Improving Supervised Learning

Zilin Ding, Yuhang Yang, Xuan Cheng +2

Self-supervised learning, which benefits from automatically constructing labels through pre-designed pretext task, has recently been applied for strengthen supervised learning. Sin…

cs.CV2026

GaussianSwap: Animatable Video Face Swapping with 3D Gaussian Splatting

Xuan Cheng, Jiahao Rao, Chengyang Li +3

We introduce GaussianSwap, a novel video face swapping framework that constructs a 3D Gaussian Splatting based face avatar from a target video while transferring identity from a so…

cs.CV2022

White Paper Assistance: A Step Forward Beyond the Shortcut Learning

Xuan Cheng, Tianshu Xie, Xiaomin Wang +3

The promising performances of CNNs often overshadow the need to examine whether they are doing in the way we are actually interested. We show through experiments that even over-par…