5 papers
YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
Botao Ye, Boqi Chen, Haofei Xu +2
Fast and flexible 3D scene reconstruction from unstructured image collections remains a significant challenge. We present YoNoSplat, a feedforward model that reconstructs high-qual…
HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
Xiaoyuan Wang, Yizhou Zhao, Botao Ye +6
We propose HoliGS, a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos. Unlike prior 4D Gaussian splatting and dyn…
Window Token Concatenation for Efficient Visual Large Language Models
Yifan Li, Wentao Bao, Botao Ye +4
To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sli…
Synthesizing Consistent Novel Views via 3D Epipolar Attention without Re-Training
Botao Ye, Sifei Liu, Xueting Li +2
Large diffusion models demonstrate remarkable zero-shot capabilities in novel view synthesis from a single image. However, these models often face challenges in maintaining consist…
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
Mariam Hassan, Sebastian Stapf, Ahmad Rahimi +17
We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, ou…