Saved in:
Bibliographic Details
Main Authors: Kang, Gyeongjin, Nam, Seungtae, Yang, Seungkwon, Sun, Xiangyu, Khamis, Sameh, Mohamed, Abdelrahman, Park, Eunbyung
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.23277
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913175243325440
author Kang, Gyeongjin
Nam, Seungtae
Yang, Seungkwon
Sun, Xiangyu
Khamis, Sameh
Mohamed, Abdelrahman
Park, Eunbyung
author_facet Kang, Gyeongjin
Nam, Seungtae
Yang, Seungkwon
Sun, Xiangyu
Khamis, Sameh
Mohamed, Abdelrahman
Park, Eunbyung
contents 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 3D Gaussian splatting, has attracted significant attention due to its fast and high-quality rendering. However, many state-of-the-art methods, primarily based on transformer architectures, suffer from severe scalability issues because they rely on full attention across image tokens from multiple input views, resulting in prohibitive computational costs as the number of views or image resolution increases. Toward a scalable and efficient feed-forward 3D reconstruction, we introduce an iterative Large 3D Reconstruction Model (iLRM) that generates 3D Gaussian representations through an iterative refinement mechanism, guided by three core principles: (1) decoupling the scene representation from input images to enable compact 3D representations; (2) decomposing global multi-view interactions into a two-stage attention scheme to reduce computational costs; and (3) injecting high-resolution information at every layer to achieve high-fidelity reconstruction. Experimental results on widely used datasets, such as RE10K and DL3DV, demonstrate that iLRM outperforms existing methods in both reconstruction quality and speed.
format Preprint
id arxiv_https___arxiv_org_abs_2507_23277
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle iLRM: An Iterative Large 3D Reconstruction Model
Kang, Gyeongjin
Nam, Seungtae
Yang, Seungkwon
Sun, Xiangyu
Khamis, Sameh
Mohamed, Abdelrahman
Park, Eunbyung
Computer Vision and Pattern Recognition
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 3D Gaussian splatting, has attracted significant attention due to its fast and high-quality rendering. However, many state-of-the-art methods, primarily based on transformer architectures, suffer from severe scalability issues because they rely on full attention across image tokens from multiple input views, resulting in prohibitive computational costs as the number of views or image resolution increases. Toward a scalable and efficient feed-forward 3D reconstruction, we introduce an iterative Large 3D Reconstruction Model (iLRM) that generates 3D Gaussian representations through an iterative refinement mechanism, guided by three core principles: (1) decoupling the scene representation from input images to enable compact 3D representations; (2) decomposing global multi-view interactions into a two-stage attention scheme to reduce computational costs; and (3) injecting high-resolution information at every layer to achieve high-fidelity reconstruction. Experimental results on widely used datasets, such as RE10K and DL3DV, demonstrate that iLRM outperforms existing methods in both reconstruction quality and speed.
title iLRM: An Iterative Large 3D Reconstruction Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.23277