collaborators

6 papers

cs.CV2025

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

Jiahao Wang, Yufeng Yuan, Rujie Zheng +12

Significant progress has been made in spatial intelligence, spanning both spatial reconstruction and world exploration. However, the scalability and real-world fidelity of current…

cs.CV2025

TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond

Yifei Zeng, Yajie Bao, Jiachen Qian +7

Prevailing 3D texture generation methods, which often rely on multi-view fusion, are frequently hindered by inter-view inconsistencies and incomplete coverage of complex surfaces,…

cs.CV2025

ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral Probes

Jian Gao, Mengqi Yuan, Yifei Zeng +8

Gaussian Splatting (GS) enables immersive rendering, but realistic 3D object-scene composition remains challenging. Baked appearance and shadow information in GS radiance fields ca…

cs.CV2025

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Shuang Wu, Youtian Lin, Feihu Zhang +8

Generating high-resolution 3D shapes using volumetric representations such as Signed Distance Functions (SDFs) presents substantial computational and memory challenges. We introduc…

cs.CV2025

Matrix3D: Large Photogrammetry Model All-in-One

Yuanxun Lu, Jingyang Zhang, Tian Fang +6

We present Matrix3D, a unified model that performs several photogrammetry subtasks, including pose estimation, depth prediction, and novel view synthesis using just the same model.…

cs.CV2025

Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors

Lin-Zhuo Chen, Kangjie Liu, Youtian Lin +4

3D Gaussian Splatting (3DGS) has achieved excellent rendering quality with fast training and rendering speed. However, its optimization process lacks explicit geometric constraints…