5 papers
DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming
Zhihui Ke, Yuyang Liu, Xiaobo Zhou +1
3D Gaussian Splatting~(3DGS) has emerged as a promising paradigm for reconstructing streamable free-viewpoint video~(FVV) from multi-view videos. However, 3DGS-based FVVs typically…
StreamSTGS: Streaming Spatial and Temporal Gaussian Grids for Real-Time Free-Viewpoint Video
Zhihui Ke, Yuyang Liu, Xiaobo Zhou +1
Streaming free-viewpoint video~(FVV) in real-time still faces significant challenges, particularly in training, rendering, and transmission efficiency. Harnessing superior performa…
TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction
DaDong Jiang, Zhihui Ke, Xiaobo Zhou +5
Dynamic scene reconstruction is a long-term challenge in 3D vision. Recent methods extend 3D Gaussian Splatting to dynamic scenes via additional deformation fields and apply explic…
FlexiTex: Enhancing Texture Generation via Visual Guidance
DaDong Jiang, Xianghui Yang, Zibo Zhao +7
Recent texture generation methods achieve impressive results due to the powerful generative prior they leverage from large-scale text-to-image diffusion models. However, abstract t…
GSVR: 2D Gaussian-based Video Representation for 800+ FPS with Hybrid Deformation Field
Zhizhuo Pang, Zhihui Ke, Xiaobo Zhou +1
Implicit neural representations for video have been recognized as a novel and promising form of video representation. Existing works pay more attention to improving video reconstru…