52 citations · 67 across the 15 of their papers we have counts for
14 papers · 1 filter
EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video
Yuan Zeng, Yujia Shi, Tiao Tan +6
Estimating full-hand grasp pressure from egocentric video is critical for immersive VR and robotic manipulation, yet dense tactile sensing often relies on intrusive hardware. Exist…
Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
Yuan Zeng, Yujia Shi, Yuhao Yang +4
Human image animation aims to generate a video from a static reference image, guided by pose information extracted from a driving video. Existing approaches often rely on pose esti…
FreeAnimate: Training-Free Human Image Animation with Preview-Guided Denoising
Yuan Zeng, Yujia Shi, Zongqing Lu +1
Human Image Animation has seen significant advancements, primarily driven by diffusion models. However, existing methods typically demand substantial training data and resources to…
EgoPressDiff: Multimodal Video Diffusion for Egocentric UV-Domain Hand-Pressure Estimation
Yuan Zeng, Zilue Gao, Yujia Shi +3
Estimating hand-surface contact pressure from an egocentric view is crucial for AR/VR devices, robotic imitation, and ergonomic analysis. Existing methods often discretize pressure…
SMPLX-Lite: A Realistic and Drivable Avatar Benchmark with Rich Geometry and Texture Annotations
Yujiao Jiang, Qingmin Liao, Zhaolong Wang +7
Recovering photorealistic and drivable full-body avatars is crucial for numerous applications, including virtual reality, 3D games, and tele-presence. Most methods, whether reconst…
OccGaussian: 3D Gaussian Splatting for Occluded Human Rendering
Jingrui Ye, Zongkai Zhang, Yujiao Jiang +3
Rendering dynamic 3D human from monocular videos is crucial for various applications such as virtual reality and digital entertainment. Most methods assume the people is in an unob…
UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modeling
Yujiao Jiang, Qingmin Liao, Xiaoyu Li +5
Reconstructing photo-realistic drivable human avatars from multi-view image sequences has been a popular and challenging topic in the field of computer vision and graphics. While e…
LLA-FLOW: A Lightweight Local Aggregation on Cost Volume for Optical Flow Estimation
Jiawei Xu, Zongqing Lu, Qingmin Liao
Lack of texture often causes ambiguity in matching, and handling this issue is an important challenge in optical flow estimation. Some methods insert stacked transformer modules th…
APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation
Jiacheng Chen, Bin-Bin Gao, Zongqing Lu +3
Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning…
SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes
Jiacheng Chen, Bin-Bin Gao, Zongqing Lu +3
Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Most of advanced solutions exploit a metri…
A region-based descriptor network for uniformly sampled keypoints
Kai Lv, Zongqing Lu, Qingmin Liao
Matching keypoint pairs of different images is a basic task of computer vision. Most methods require customized extremum point schemes to obtain the coordinates of feature points w…
Noise-Sampling Cross Entropy Loss: Improving Disparity Regression Via Cost Volume Aware Regularizer
Yang Chen, Zongqing Lu, Xuechen Zhang +2
Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance. However, many well-acknowledged specific properties of disparity est…
XSepConv: Extremely Separated Convolution
Jiarong Chen, Zongqing Lu, Jing-Hao Xue +1
Depthwise convolution has gradually become an indispensable operation for modern efficient neural networks and larger kernel sizes () have been applied to it recently. In thi…
Optical Flow Super-Resolution Based on Image Guidence Using Convolutional Neural Network
Liping Zhang, Zongqing Lu, Qingmin Liao
The convolutional neural network model for optical flow estimation usually outputs a low-resolution(LR) optical flow field. To obtain the corresponding full image resolution,interp…