Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2501.13928 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910885083086848 |
|---|---|
| author | Yang, Jianing Sax, Alexander Liang, Kevin J. Henaff, Mikael Tang, Hao Cao, Ang Chai, Joyce Meier, Franziska Feiszli, Matt |
| author_facet | Yang, Jianing Sax, Alexander Liang, Kevin J. Henaff, Mikael Tang, Hao Cao, Ang Chai, Joyce Meier, Franziska Feiszli, Matt |
| contents | Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a fundamentally pairwise approach, processing images in pairs and necessitating costly global alignment procedures to reconstruct from multiple views. In this work, we propose Fast 3D Reconstruction (Fast3R), a novel multi-view generalization to DUSt3R that achieves efficient and scalable 3D reconstruction by processing many views in parallel. Fast3R's Transformer-based architecture forwards N images in a single forward pass, bypassing the need for iterative alignment. Through extensive experiments on camera pose estimation and 3D reconstruction, Fast3R demonstrates state-of-the-art performance, with significant improvements in inference speed and reduced error accumulation. These results establish Fast3R as a robust alternative for multi-view applications, offering enhanced scalability without compromising reconstruction accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13928 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass Yang, Jianing Sax, Alexander Liang, Kevin J. Henaff, Mikael Tang, Hao Cao, Ang Chai, Joyce Meier, Franziska Feiszli, Matt Computer Vision and Pattern Recognition Artificial Intelligence Graphics Robotics Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a fundamentally pairwise approach, processing images in pairs and necessitating costly global alignment procedures to reconstruct from multiple views. In this work, we propose Fast 3D Reconstruction (Fast3R), a novel multi-view generalization to DUSt3R that achieves efficient and scalable 3D reconstruction by processing many views in parallel. Fast3R's Transformer-based architecture forwards N images in a single forward pass, bypassing the need for iterative alignment. Through extensive experiments on camera pose estimation and 3D reconstruction, Fast3R demonstrates state-of-the-art performance, with significant improvements in inference speed and reduced error accumulation. These results establish Fast3R as a robust alternative for multi-view applications, offering enhanced scalability without compromising reconstruction accuracy. |
| title | Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Robotics |
| url | https://arxiv.org/abs/2501.13928 |