Saved in:
| Main Authors: | , , , , , , |
|---|---|
| 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 |