6 papers · 1 filter
Edit3r: Instant 3D Scene Editing from Sparse Unposed Images
Jiageng Liu, Weijie Lyu, Xueting Li +2
We present Edit3r, a feed-forward framework that reconstructs and edits 3D scenes in a single pass from unposed, view-inconsistent, instruction-edited images. Unlike prior methods…
Pursuing Minimal Sufficiency in Spatial Reasoning
Yejie Guo, Yunzhong Hou, Wufei Ma +2
Spatial reasoning, the ability to ground language in 3D understanding, remains a persistent challenge for Vision-Language Models (VLMs). We identify two fundamental bottlenecks: in…
CoCo4D: Comprehensive and Complex 4D Scene Generation
Junwei Zhou, Xueting Li, Lu Qi +1
Existing 4D synthesis methods primarily focus on object-level generation or dynamic scene synthesis with limited novel views, restricting their ability to generate multi-view consi…
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…
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…
No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
Botao Ye, Sifei Liu, Haofei Xu +4
We introduce NoPoSplat, a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from \textit{unposed} sparse multi-view images. Our model, trained ex…