activity
20242026
collaborators

26 papers

cs.CV2026

EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation

Runsong Zhu, Jiaxin Guo, Xiaoyang Guo +9

This paper introduces EPS3D, a new end-to-end feed-forward framework for open-vocabulary 3D panoptic segmentation. Unlike existing methods relying on additional preprocessing, we d…

cs.CV2026

Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping

Peilin Tao, Chong Cheng, Yuansen Du +8

Long-horizon online visual mapping is a core capability for robot perception, requiring continuous camera-motion and scene-geometry estimation from visual streams under bounded mem…

cs.CV2026

HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction

Chong Cheng, Peilin Tao, Nanjie Yao +9

Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer from drift, jitter, or…

cs.CV2026

HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation

Conglang Zhang, Yifan Zhan, Qingjie Wang +10

Closed-loop driving simulation requires real-time interaction beyond short offline clips, pushing current driving world models toward autoregressive (AR) rollout. Existing AR disti…

cs.CV2026

EponaV2: Driving World Model with Comprehensive Future Reasoning

Jiawei Xu, Zhizhou Zhong, Zhijian Shu +8

Data scaling plays a pivotal role in the pursuit of general intelligence. However, the prevailing perception-planning paradigm in autonomous driving relies heavily on expensive man…

cs.CV2026

Is Your Driving World Model an All-Around Player?

Lingdong Kong, Ao Liang, Tianyi Yan +20

Today's driving world models can generate remarkably realistic dash-cam videos, yet no single model excels universally. Some generate photorealistic textures but violate basic phys…