12 papers
LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
Zhengqin Li, Cheng Zhang, Jakob Engel +1
We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction. Although recent object-centric feed-forw…
ART: Articulated Reconstruction Transformer
Zizhang Li, Cheng Zhang, Zhengqin Li +7
We introduce ART, Articulated Reconstruction Transformer -- a category-agnostic, feed-forward model that reconstructs complete 3D articulated objects from only sparse, multi-state…
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
Ahan Shabanov, Peter Hedman, Ethan Weber +10
We present Free-Range Gaussians, a multi-view reconstruction method that predicts non-pixel, non-voxel-aligned 3D Gaussians from as few as four images. This is done through flow ma…
ShapeR: Robust Conditional 3D Shape Generation from Casual Captures
Yawar Siddiqui, Duncan Frost, Samir Aroudj +9
Recent advances in 3D shape generation have achieved impressive results, but most existing methods rely on clean, unoccluded, and well-segmented inputs. Such conditions are rarely…
4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos
Zhen Xu, Zhengqin Li, Zhao Dong +3
We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bi…
3D Mesh Editing using Masked LRMs
Will Gao, Dilin Wang, Yuchen Fan +6
We present a novel approach to shape editing, building on recent progress in 3D reconstruction from multi-view images. We formulate shape editing as a conditional reconstruction pr…