25 citations · 32 across the 22 of their papers we have counts for
12 papers · 1 filter
UnIRe: Unsupervised Instance Decomposition for Dynamic Urban Scene Reconstruction
Yunxuan Mao, Rong Xiong, Yue Wang +1
Reconstructing and decomposing dynamic urban scenes is crucial for autonomous driving, urban planning, and scene editing. However, existing methods fail to perform instance-aware d…
PanopticSplatting: End-to-End Panoptic Gaussian Splatting
Yuxuan Xie, Xuan Yu, Changjian Jiang +5
Open-vocabulary panoptic reconstruction is a challenging task for simultaneous scene reconstruction and understanding. Recently, methods have been proposed for 3D scene understandi…
CNSv2: Probabilistic Correspondence Encoded Neural Image Servo
Anzhe Chen, Hongxiang Yu, Shuxin Li +5
Visual servo based on traditional image matching methods often requires accurate keypoint correspondence for high precision control. However, keypoint detection or matching tends t…
Leverage Cross-Attention for End-to-End Open-Vocabulary Panoptic Reconstruction
Xuan Yu, Yuxuan Xie, Yili Liu +4
Open-vocabulary panoptic reconstruction offers comprehensive scene understanding, enabling advances in embodied robotics and photorealistic simulation. In this paper, we propose Pa…
Scale Disparity of Instances in Interactive Point Cloud Segmentation
Chenrui Han, Xuan Yu, Yuxuan Xie +5
Interactive point cloud segmentation has become a pivotal task for understanding 3D scenes, enabling users to guide segmentation models with simple interactions such as clicks, the…
Let Occ Flow: Self-Supervised 3D Occupancy Flow Prediction
Yili Liu, Linzhan Mou, Xuan Yu +4
Accurate perception of the dynamic environment is a fundamental task for autonomous driving and robot systems. This paper introduces Let Occ Flow, the first self-supervised work fo…
PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction
Xuan Yu, Yili Liu, Chenrui Han +5
Panoptic reconstruction is a challenging task in 3D scene understanding. However, most existing methods heavily rely on pre-trained semantic segmentation models and known 3D object…
-DBA: Neural Implicit Dense Bundle Adjustment Enables Image-Only Driving Scene Reconstruction
Yunxuan Mao, Bingqi Shen, Yifei Yang +4
The joint optimization of the sensor trajectory and 3D map is a crucial characteristic of bundle adjustment (BA), essential for autonomous driving. This paper presents -DBA, a n…
EDA: Evolving and Distinct Anchors for Multimodal Motion Prediction
Longzhong Lin, Xuewu Lin, Tianwei Lin +3
Motion prediction is a crucial task in autonomous driving, and one of its major challenges lands in the multimodality of future behaviors. Many successful works have utilized mixtu…
Semantics-aware Motion Retargeting with Vision-Language Models
Haodong Zhang, ZhiKe Chen, Haocheng Xu +6
Capturing and preserving motion semantics is essential to motion retargeting between animation characters. However, most of the previous works neglect the semantic information or r…
DORec: Decomposed Object Reconstruction and Segmentation Utilizing 2D Self-Supervised Features
Jun Wu, Sicheng Li, Sihui Ji +4
Recovering 3D geometry and textures of individual objects is crucial for many robotics applications, such as manipulation, pose estimation, and autonomous driving. However, decompo…
Leveraging BEV Representation for 360-degree Visual Place Recognition
Xuecheng Xu, Yanmei Jiao, Sha Lu +3
This paper investigates the advantages of using Bird's Eye View (BEV) representation in 360-degree visual place recognition (VPR). We propose a novel network architecture that util…