6 papers
MoWorld: A Flash World Model
Team Moxin, Deyi Ji, Tianrun Chen +37
The future of World Models depends not only on scaling model capability, but also on scaling practicality and inference efficiency. High-frame-rate inference enables responsive per…
4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation
Ying Zang, Xuanyi Liu, Yidong Han +9
Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric priors, their performance s…
Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors
Ying Zang, Yidong Han, Chaotao Ding +8
Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences whe…
HD-VGGT: High-Resolution Visual Geometry Transformer
Tianrun Chen, Yuanqi Hu, Yidong Han +11
High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forward approaches, such as the Visua…
SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation
Tianrun Chen, Runlong Cao, Xinda Yu +8
The rapid rise of large-scale foundation models has reshaped the landscape of image segmentation, with models such as Segment Anything achieving unprecedented versatility across di…
Syllables to Scenes: Literary-Guided Free-Viewpoint 3D Scene Synthesis from Japanese Haiku
Chunan Yu, Yidong Han, Chaotao Ding +6
In the era of the metaverse, where immersive technologies redefine human experiences, translating abstract literary concepts into navigable 3D environments presents a fundamental c…