RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models
Yaoyang Liu*, Dongyu Yan*, Yihua Du, Shengju Qian, Zeke Xie, Xin Wang, Ying-Cong Chen, Long Chen.
arXiv preprint (2026)
arXiv / Paper / GitHub / Project Page

We propose Rate-Adaptive Rollout (RAR), which decouples the temporal rate of interactive world models from generation throughput. Stride-RoPE and synchronized multi-stride sampling support temporally consistent rollout across different rates, including unseen rates and online rate switching, while extending the physical-time horizon.

UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
Tanghui Jia*, Dongyu Yan*, Dehao Hao*, Yang Li, Kaiyi Zhang, Xianyi He, Lanjiong Li, Yuhan Wang, Jinnan Chen, Lutao Jiang, Qishen Yin, Long Quan, Ying-Cong Chen, Li Yuan.
arXiv preprint (2025)
arXiv / Paper / GitHub / Project Page

We present a scalable two-stage 3D diffusion framework that first generates coarse geometry and then refines it into detailed, high-fidelity shapes. Geometry-aware refinement and a watertight data-processing pipeline help preserve fine details and improve generation quality.

FlexPainter: Flexible and Multi-View Consistent Texture Generation
Dongyu Yan*, Leyi Wu*, Jiantao Lin, Luozhou Wang, Tianshuo Xu, Zhifei Chen, Zhen Yang, Lie Xu, Shunsi Zhang, Ying-Cong Chen.
arXiv preprint (2025)
arXiv / Paper / GitHub / Project Page

We introduce FlexPainter, a texture generation pipeline that supports flexible guidance from text, images, or both. Joint multi-view generation, view synchronization, and 3D-aware texture completion enable consistent, high-resolution textures for 3D assets.

MSI-NeRF: Linking Omni-Depth with View Synthesis through Multi-Sphere Image aided Generalizable Neural Radiance Field
Dongyu Yan, Guanyu Huang, Fengyu Quan, Haoyao Chen.
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)
arXiv / Paper / Video / GitHub

We propose a generalizable NeRF framework that takes four fisheye images as input and produces a 3D MSI representation for novel view synthesis and depth estimation. Trained using only synthetic depth data, the framework generalizes to a wide range of scenarios. We also release a fisheye multi-view dataset for training and evaluation.

Active Implicit Object Reconstruction using Uncertainty-guided Next-Best-View Optimization
Dongyu Yan*, Jianheng Liu*, Fengyu Quan, Haoyao Chen.
IEEE Robotics and Automation Letters (RA-L 2023)
arXiv / Paper / Video / GitHub

We propose an active implicit object reconstruction method that uses uncertainty estimates from an implicit occupancy map to guide next-best-view optimization. The method optimizes a virtual camera trajectory through the uncertainty field to maximize information gain during reconstruction.

Efficient Implicit Neural Reconstruction Using LiDAR
Dongyu Yan, Xiaoyang Lyu, Jieqi Shi, Yi Lin.
IEEE International Conference on Robotics and Automation (ICRA 2023)
arXiv / Paper / Video / GitHub / Project Page

We propose an efficient and accurate implicit reconstruction method using LiDAR scans that is applicable across a range of scenarios. Our self-collected dataset demonstrates its effectiveness in real-world scenes, even with sparse LiDAR scans and poorly aligned poses.