Chuhua Xian
YOU?
Author Swipe
View article: Identity-Preserving Video Dubbing Using Motion Warping
Identity-Preserving Video Dubbing Using Motion Warping Open
Video dubbing aims to synthesize realistic, lip-synced videos from a reference video and a driving audio signal. Although existing methods can accurately generate mouth shapes driven by audio, they often fail to preserve identity-specific …
View article: Accelerate Neural Subspace-Based Reduced-Order Solver of Deformable Simulation by Lipschitz Optimization
Accelerate Neural Subspace-Based Reduced-Order Solver of Deformable Simulation by Lipschitz Optimization Open
Reduced-order simulation is an emerging method for accelerating physical simulations with high DOFs, and recently developed neural-network-based methods with nonlinear subspaces have been proven effective in diverse applications as more co…
View article: Delving into high-quality SVBRDF acquisition: A new setup and method
Delving into high-quality SVBRDF acquisition: A new setup and method Open
In this study, we present a new and innovative framework for acquiring high-quality SVBRDF maps. Our approach addresses the limitations of the current methods and proposes a new solution. The core of our method is a simple hardware setup c…
View article: VSGAN: Visual Saliency guided Generative Adversarial Network for data augmentation
VSGAN: Visual Saliency guided Generative Adversarial Network for data augmentation Open
International audience
View article: Consistent Depth Prediction under Various Illuminations using Dilated Cross Attention
Consistent Depth Prediction under Various Illuminations using Dilated Cross Attention Open
In this paper, we aim to solve the problem of consistent depth prediction in complex scenes under various illumination conditions. The existing indoor datasets based on RGB-D sensors or virtual rendering have two critical limitations - spa…
View article: Multi-Scale Fusion Networks with RGB Image Features for Depth Map Completion
Multi-Scale Fusion Networks with RGB Image Features for Depth Map Completion Open
Currently, researchers cannot directly train end-to-end model for depth image completion because of lacking paired “incomplete-complete” RGB-D datasets. To address this problem, a random mask-based method which is combined with “real-synth…
View article: Multi-Scale Progressive Fusion Learning for Depth Map Super-Resolution
Multi-Scale Progressive Fusion Learning for Depth Map Super-Resolution Open
Limited by the cost and technology, the resolution of depth map collected by depth camera is often lower than that of its associated RGB camera. Although there have been many researches on RGB image super-resolution (SR), a major problem w…
View article: Fast Generation of High Fidelity RGB-D Images by Deep-Learning with Adaptive Convolution
Fast Generation of High Fidelity RGB-D Images by Deep-Learning with Adaptive Convolution Open
Using the raw data from consumer-level RGB-D cameras as input, we propose a deep-learning based approach to efficiently generate RGB-D images with completed information in high resolution. To process the input images in low resolution with…
View article: DeepAO: Efficient Screen Space Ambient Occlusion Generation via Deep Network
DeepAO: Efficient Screen Space Ambient Occlusion Generation via Deep Network Open
Ambient occlusion (abbr. AO) plays an important role in realistic rendering applications because AO produces more realistic ambient lighting, which is achieved by calculating the brightness of certain screen parts based on objects' geometr…