Jiansong Pei — accepted AI-conference papers

2026

Animator-Centric Skeleton Generation on Objects with Fine-Grained Details

Mingze Sun, Cheng Zeng, Jiansong Pei, Junhao Chen, Chaoyue Song, Shaohui Wang +4

CVPR 2026

Skeleton generation is essential for animating 3D assets, but current deep learning methods remain limited: they cannot handle the growing structural complexity of modern models and offer minimal controllability, creating a major bottleneck for real-world animation workflows. To address this, we pro

Cited by 0 Source ↗Scholar ↗

2025

Knowledge-Driven Visual Target Navigation: Dual Graph Navigation

Shiyao Li, Ziyang Meng, Jiansong Pei, Jiahao Chen, Bingcheng Dong, Guangsheng Li +2

ICRA 2025

In unknown environments, navigating a robot by a given image to a specific location or instance is critical and challenging. The existing end-to-end approaches require simultaneous implicit learning of multiple subtasks, and modular approaches depend on metric information. Both approaches face high

Cited by 0 Source ↗code ↗Scholar ↗