activity
20242026
collaborators

5 papers

cs.CV2026

Scene-SAM3D: Multi-View Scene Asset Generation Without Fine-Tuning

Yuqi Zhang, Yadan Luo, Xiangyu Sun +3

High-quality 3D scene assets are critical for embodied applications such as robotic manipulation, navigation, and simulation. Despite their strong object priors, recent single-imag…

cs.CV2026

2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting

Hwasik Jeong, Seungryong Lee, Gyeongjin Kang +4

Pose-free feed-forward 3D Gaussian Splatting (3DGS) has opened a new frontier for rapid 3D modeling, enabling high-quality Gaussian representations to be generated from uncalibrate…

cs.CV2026

VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model

Xiangyu Sun, Shijie Wang, Fengyi Zhang +5

World models that forecast scene evolution by generating future video frames devote the bulk of their capacity to photometric details, yet the resulting predictions often remain ge…

cs.CV2025

Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting

Xiangyu Sun, Runnan Chen, Mingming Gong +2

Sparse-view scene reconstruction often faces significant challenges due to the constraints imposed by limited observational data. These limitations result in incomplete information…

cs.CV2024

OVGaussian: Generalizable 3D Gaussian Segmentation with Open Vocabularies

Runnan Chen, Xiangyu Sun, Zhaoqing Wang +8

Open-vocabulary scene understanding using 3D Gaussian (3DGS) representations has garnered considerable attention. However, existing methods mostly lift knowledge from large 2D visi…