23 papers
SelectOccFlow: Selective Spatiotemporal Aggregation for 3D Occupancy and Scene Flow Prediction
Yuhang Wang, Kai Luo, Yuanfan Zheng +1
Comprehensive 3D scene understanding for autonomous driving requires modeling geometry, semantics, and motion. However, camera-based occupancy and scene flow prediction are sensiti…
EmbPASS: Towards Cross-Embodiment Open Panoramic Segmentation
Pujun Guo, Yuanfan Zheng, Fei Teng +5
Panoramic images provide a complete 360-degree field of view, enabling comprehensive scene understanding for embodied perception. However, heterogeneous embodied platforms exhibit…
FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters
Wenya Su, Kai Luo, Di Wen +5
Fisheye cameras give mobile robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely reuse fail on them: strong r…
UniTrackPLA: Unified Panorama-Language-Action Model for Instruction-Guided Navigation and Dynamic Person Tracking
Pengfei Qi, Haoran Lin, Sizhuang Chen +7
General-purpose embodied robots should support both navigation toward language-specified destinations and dynamic person tracking under arbitrary initial target azimuths. However,…
PanoFuse: Panorama-Enhanced Vision-Language-Action Learning with Decoupled Semantic-Geometric Routing
Peng Xu, Haoran Lin, Wanjun Jia +4
Vision-Language-Action (VLA) policies have shown promising performance in language-conditioned robotic manipulation. However, most existing VLA systems rely on conventional perspec…
Spheriverse: 3D Scene Understanding from Spherical Observations in the Wild
Fei Teng, Sheng Wu, Mengfei Duan +7
Spherical observations provide global visual context for 3D scene understanding. However, visual information is encoded in an angular domain, whereas the physical world is represen…
PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking
Kai Luo, Fei Teng, Mengfei Duan +6
We introduce Point-supervised Multi-Object Tracking (PS-MOT) as a cost-effective alternative to traditional bounding box supervision, shifting the focus from spatial fitting to top…
CylindTrack: Depth-Aware Cylindrical Motion Modeling for Panoramic Multi-Object Tracking
Buyin Deng, Kai Luo, Lingxin Huang +5
Multi-Object Tracking (MOT) is essential for embodied perception, where panoramic cameras provide a 360° field of view to reduce blind spots and keep surrounding targets observable…
Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robots
Guoqiang Zhao, Zhe Yang, Sheng Wu +5
Panoramic imagery provides holistic 360° visual coverage for environmental perception in quadruped robots. However, existing occupancy prediction methods are primarily designed for…
OccTrack360: 4D Panoptic Occupancy Tracking from Surround-View Fisheye Cameras
Yongzhi Lin, Kai Luo, Yuanfan Zheng +4
Understanding dynamic 3D environments in a spatially continuous and temporally consistent manner is fundamental for robotics and autonomous driving. While recent advances in occupa…
Spherical-GOF: Geometry-Aware Panoramic Gaussian Opacity Fields for 3D Scene Reconstruction
Zhe Yang, Guoqiang Zhao, Sheng Wu +2
Omnidirectional images are increasingly used in robotics and vision due to their wide field of view. However, extending 3D Gaussian Splatting (3DGS) to panoramic camera models rema…
NOVA: Next-step Open-Vocabulary Autoregression for 3D Multi-Object Tracking in Autonomous Driving
Kai Luo, Xu Wang, Rui Fan +1
Generalizing across unknown targets is critical for open-world perception, yet existing 3D Multi-Object Tracking (3D MOT) pipelines remain limited by closed-set assumptions and ``s…
OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback
Kai Luo, Hao Shi, Kunyu Peng +4
To address panoramic distortion, large search space, and identity ambiguity under a 360° FoV, OmniTrack++ adopts a feedback-driven framework that progressively refines perception w…
DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Tracking
Buyin Deng, Lingxin Huang, Kai Luo +2
Visual Multi-Object Tracking (MOT) is a crucial component of robotic perception, yet existing Tracking-By-Detection (TBD) methods often rely on 2D cues, such as bounding boxes and…
CoBEVMoE: Heterogeneity-aware Feature Fusion with Dynamic Mixture-of-Experts for Collaborative Perception
Lingzhao Kong, Jiacheng Lin, Siyu Li +3
Collaborative perception aims to extend sensing coverage and improve perception accuracy by sharing information among multiple agents. However, due to differences in viewpoints and…
Segment-to-Act: Label-Noise-Robust Action-Prompted Video Segmentation Towards Embodied Intelligence
Wenxin Li, Kunyu Peng, Di Wen +4
Embodied intelligence relies on accurately segmenting objects actively involved in interactions. Action-based video object segmentation addresses this by linking segmentation with…
QuaDreamer: Controllable Panoramic Video Generation for Quadruped Robots
Sheng Wu, Fei Teng, Hao Shi +4
Panoramic cameras, capturing comprehensive 360-degree environmental data, are suitable for quadruped robots in surrounding perception and interaction with complex environments. How…
Hallucinating 360°: Panoramic Street-View Generation via Local Scenes Diffusion and Probabilistic Prompting
Fei Teng, Kai Luo, Sheng Wu +6
Panoramic perception holds significant potential for autonomous driving, enabling vehicles to acquire a comprehensive 360° surround view in a single shot. However, autonomous drivi…
Out-of-Distribution Semantic Occupancy Prediction
Yuheng Zhang, Mengfei Duan, Kunyu Peng +6
3D semantic occupancy prediction is crucial for autonomous driving, providing a dense, semantically rich environmental representation. However, existing methods focus on in-distrib…
Panoramic Out-of-Distribution Segmentation
Mengfei Duan, Yuheng Zhang, Yihong Cao +5
Panoramic imaging enables capturing 360° images with an ultra-wide Field-of-View (FoV) for dense omnidirectional perception, which is critical to applications such as autonomous dr…
Omnidirectional Multi-Object Tracking
Kai Luo, Hao Shi, Sheng Wu +6
Panoramic imagery, with its 360° field of view, offers comprehensive information to support Multi-Object Tracking (MOT) in capturing spatial and temporal relationships of surroundi…
Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance
Jiayi Zhao, Fei Teng, Kai Luo +4
The perception capability of robotic systems relies on the richness of the dataset. Although Segment Anything Model 2 (SAM2), trained on large datasets, demonstrates strong percept…
LFX: Towards Unified Light Field Dense Semantic Segmentation and Salient Object Detection
Fei Teng, Lingxin Huang, Buyin Deng +8
Light field cameras capture multi-view observations within a single exposure. However, existing studies are typically tailored to specific LF representations, leaving the field wit…