4 papers
ERMV: Editing 4D Robotic Multi-view images to enhance embodied agents
Chang Nie, Guangming Wang, Zhe Lie +1
Robot imitation learning relies on 4D multi-view sequential images. However, the high cost of data collection and the scarcity of high-quality data severely constrain the generaliz…
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…
SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations
Krispin Wandel, Hesheng Wang
Semantic correspondence made tremendous progress through the recent advancements of large vision models (LVM). While these LVMs have been shown to reliably capture local semantics,…
PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environments
Haoang Li, Xiangqi Meng, Xingxing Zuo +3
Simultaneous localization and mapping (SLAM) has achieved impressive performance in static environments. However, SLAM in dynamic environments remains an open question. Many method…