activity
20162024
most cited3D Hand Pose Tracking and Estimation Using Stereo Matching

122 citations · 146 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV20243 cited

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

Jiahe Li, Jiawei Zhang, Xiao Bai +4

Radiance fields have demonstrated impressive performance in synthesizing novel views from sparse input views, yet prevailing methods suffer from high training costs and slow infere…

cs.CV2024

Robust Synthetic-to-Real Transfer for Stereo Matching

Jiawei Zhang, Jiahe Li, Lei Huang +4

With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains. However, few studies have in…

cs.CV20231 cited

FusionViT: Hierarchical 3D Object Detection via LiDAR-Camera Vision Transformer Fusion

Xinhao Xiang, Jiawei Zhang

For 3D object detection, both camera and lidar have been demonstrated to be useful sensory devices for providing complementary information about the same scenery with data represen…

cs.CV20235 cited

Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

Jiahe Li, Jiawei Zhang, Xiao Bai +2

This paper presents ER-NeRF, a novel conditional Neural Radiance Fields (NeRF) based architecture for talking portrait synthesis that can concurrently achieve fast convergence, rea…

cs.CV2023

Generic Attention-model Explainability by Weighted Relevance Accumulation

Yiming Huang, Aozhe Jia, Xiaodan Zhang +1

Attention-based transformer models have achieved remarkable progress in multi-modal tasks, such as visual question answering. The explainability of attention-based methods has rece…

cs.CV2023

RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs

Zhouxia Wang, Jiawei Zhang, Tianshui Chen +2

Blind face restoration aims at recovering high-quality face images from those with unknown degradations. Current algorithms mainly introduce priors to complement high-quality detai…