44 citations · 69 across the 21 of their papers we have counts for
21 papers
Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction
Weiyi Xue, Fan Lu, Chi Zhang +6
3D Gaussian Splatting has demonstrated remarkable potential in novel view synthesis. In contrast to small-scale scenes, large-scale scenes inevitably contain sparsely observed regi…
UrbanCraft: Urban View Extrapolation via Hierarchical Sem-Geometric Priors
Tianhang Wang, Fan Lu, Sanqing Qu +5
Existing neural rendering-based urban scene reconstruction methods mainly focus on the Interpolated View Synthesis (IVS) setting that synthesizes from views close to training camer…
Range and Bird's Eye View Fused Cross-Modal Visual Place Recognition
Jianyi Peng, Fan Lu, Bin Li +3
Image-to-point cloud cross-modal Visual Place Recognition (VPR) is a challenging task where the query is an RGB image, and the database samples are LiDAR point clouds. Compared to…
GSGTrack: Gaussian Splatting-Guided Object Pose Tracking from RGB Videos
Zhiyuan Chen, Fan Lu, Guo Yu +5
Tracking the 6DoF pose of unknown objects in monocular RGB video sequences is crucial for robotic manipulation. However, existing approaches typically rely on accurate depth inform…
HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation
Tianpei Zou, Sanqing Qu, Zhijun Li +4
3D point cloud segmentation has received significant interest for its growing applications. However, the generalization ability of models suffers in dynamic scenarios due to the di…
ELF-UA: Efficient Label-Free User Adaptation in Gaze Estimation
Yong Wu, Yang Wang, Sanqing Qu +2
We consider the problem of user-adaptive 3D gaze estimation. The performance of person-independent gaze estimation is limited due to interpersonal anatomical differences. Our goal…
MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection
Boyang Peng, Sanqing Qu, Yong Wu +5
Deep learning has achieved remarkable progress in various applications, heightening the importance of safeguarding the intellectual property (IP) of well-trained models. It entails…
LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
Sanqing Qu, Tianpei Zou, Lianghua He +4
Universal Domain Adaptation (UniDA) targets knowledge transfer in the presence of both covariate and label shifts. Recently, Source-free Universal Domain Adaptation (SF-UniDA) has…
GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning
Sanqing Qu, Tianpei Zou, Florian Röhrbein +4
Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma,…
PCDepth: Pattern-based Complementary Learning for Monocular Depth Estimation by Best of Both Worlds
Haotian Liu, Sanqing Qu, Fan Lu +4
Event cameras can record scene dynamics with high temporal resolution, providing rich scene details for monocular depth estimation (MDE) even at low-level illumination. Therefore,…
Modality-Agnostic Debiasing for Single Domain Generalization
Sanqing Qu, Yingwei Pan, Guang Chen +3
Deep neural networks (DNNs) usually fail to generalize well to outside of distribution (OOD) data, especially in the extreme case of single domain generalization (single-DG) that t…
Upcycling Models under Domain and Category Shift
Sanqing Qu, Tianpei Zou, Florian Roehrbein +4
Deep neural networks (DNNs) often perform poorly in the presence of domain shift and category shift. How to upcycle DNNs and adapt them to the target task remains an important open…
TMA: Temporal Motion Aggregation for Event-based Optical Flow
Haotian Liu, Guang Chen, Sanqing Qu +4
Event cameras have the ability to record continuous and detailed trajectories of objects with high temporal resolution, thereby providing intuitive motion cues for optical flow est…
BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation
Sanqing Qu, Guang Chen, Jing Zhang +3
Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data, which is a much more pr…
HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration
Fan Lu, Guang Chen, Yinlong Liu +4
Point cloud registration is a fundamental problem in 3D computer vision. Outdoor LiDAR point clouds are typically large-scale and complexly distributed, which makes the registratio…
ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization
Sanqing Qu, Guang Chen, Zhijun Li +3
Weakly-supervised temporal action localization aims to localize action instances temporal boundary and identify the corresponding action category with only video-level labels. Trad…
PointINet: Point Cloud Frame Interpolation Network
Fan Lu, Guang Chen, Sanqing Qu +3
LiDAR point cloud streams are usually sparse in time dimension, which is limited by hardware performance. Generally, the frame rates of mechanical LiDAR sensors are 10 to 20 Hz, wh…
MoNet: Motion-based Point Cloud Prediction Network
Fan Lu, Guang Chen, Yinlong Liu +3
Predicting the future can significantly improve the safety of intelligent vehicles, which is a key component in autonomous driving. 3D point clouds accurately model 3D information…
LAP-Net: Adaptive Features Sampling via Learning Action Progression for Online Action Detection
Sanqing Qu, Guang Chen, Dan Xu +3
Online action detection is a task with the aim of identifying ongoing actions from streaming videos without any side information or access to future frames. Recent methods proposed…
An Efficient L-Shape Fitting Method for Vehicle Pose Detection with 2D LiDAR
Sanqing Qu, Guang Chen, Canbo Ye +4
Detecting vehicles with strong robustness and high efficiency has become one of the key capabilities of fully autonomous driving cars. This topic has already been widely studied by…
Self-Localization of Parking Robots Using Square-Like Landmarks
Canbo Ye, Guang Chen, Sanqing Qu +4
In this paper, we present a framework for self-localization of parking robots in a parking lot innovatively using square-like landmarks, aiming to provide a positioning solution wi…