7 papers
NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction
Xiangyu Sun, Liu Liu, Seungkwon Yang +4
Pose-Free Feed-forward 3D Gaussian Splatting (3DGS) has recently emerged as a powerful paradigm for fast scene reconstruction. However, its performance degrades significantly in lo…
Multi-view Pyramid Transformer: Look Coarser to See Broader
Gyeongjin Kang, Seungkwon Yang, Seungtae Nam +3
We propose Multi-view Pyramid Transformer (MVP), a scalable multi-view transformer architecture that directly reconstructs large 3D scenes from tens to hundreds of images in a sing…
iLRM: An Iterative Large 3D Reconstruction Model
Gyeongjin Kang, Seungtae Nam, Seungkwon Yang +4
Feed-forward 3D modeling has emerged as a promising approach for rapid and high-quality 3D reconstruction. In particular, directly generating explicit 3D representations, such as 3…
2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting
Hwasik Jeong, Seungryong Lee, Gyeongjin Kang +4
Pose-free feed-forward 3D Gaussian Splatting (3DGS) has opened a new frontier for rapid 3D modeling, enabling high-quality Gaussian representations to be generated from uncalibrate…
Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images
Xiangyu Sun, Haoyi Jiang, Liu Liu +8
Reconstructing and semantically interpreting 3D scenes from sparse 2D views remains a fundamental challenge in computer vision. Conventional methods often decouple semantic underst…
SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting
Gyeongjin Kang, Jisang Yoo, Jihyeon Park +5
We propose SelfSplat, a novel 3D Gaussian Splatting model designed to perform pose-free and 3D prior-free generalizable 3D reconstruction from unposed multi-view images. These sett…