4 citations · 12 across the 10 of their papers we have counts for
10 papers
WM-VS: Progress-Aligned World Models for Closed-Loop Visual Servoing
Guanzhong Sun, Junyi Ma, Yixuan Zhou +3
Closed-loop visual servoing requires predictions that indicate whether an action reduces task error, not only whether the action is plausible. We call this gap the prediction-contr…
MRASfM: Multi-Camera Reconstruction and Aggregation through Structure-from-Motion in Driving Scenes
Lingfeng Xuan, Chang Nie, Yiqing Xu +3
Structure from Motion (SfM) estimates camera poses and reconstructs point clouds, forming a foundation for various tasks. However, applying SfM to driving scenes captured by multi-…
FreeDriveRF: Monocular RGB Dynamic NeRF without Poses for Autonomous Driving via Point-Level Dynamic-Static Decoupling
Yue Wen, Liang Song, Yijia Liu +4
Dynamic scene reconstruction for autonomous driving enables vehicles to perceive and interpret complex scene changes more precisely. Dynamic Neural Radiance Fields (NeRFs) have rec…
MovSAM: A Single-image Moving Object Segmentation Framework Based on Deep Thinking
Chang Nie, Yiqing Xu, Guangming Wang +3
Moving object segmentation plays a vital role in understanding dynamic visual environments. While existing methods rely on multi-frame image sequences to identify moving objects, s…
RL-GSBridge: 3D Gaussian Splatting Based Real2Sim2Real Method for Robotic Manipulation Learning
Yuxuan Wu, Lei Pan, Wenhua Wu +4
Sim-to-Real refers to the process of transferring policies learned in simulation to the real world, which is crucial for achieving practical robotics applications. However, recent…
NeRFs in Robotics: A Survey
Guangming Wang, Lei Pan, Songyou Peng +7
Detailed and realistic 3D environment representations have been a long-standing goal in the fields of computer vision and robotics. The recent emergence of neural implicit represen…
SC-NeRF: Self-Correcting Neural Radiance Field with Sparse Views
Liang Song, Guangming Wang, Jiuming Liu +3
In recent studies, the generalization of neural radiance fields for novel view synthesis task has been widely explored. However, existing methods are limited to objects and indoor…
3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion
Chaokang Jiang, Guangming Wang, Yanzi Miao +1
3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid mot…
FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection
Chaokang Jiang, Guangming Wang, Jinxing Wu +2
Promising complementarity exists between the texture features of color images and the geometric information of LiDAR point clouds. However, there still present many challenges for…
Pseudo-LiDAR for Visual Odometry
Huiying Deng, Guangming Wang, Zhiheng Feng +4
In the existing methods, LiDAR odometry shows superior performance, but visual odometry is still widely used for its price advantage. Conventionally, the task of visual odometry ma…