Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912476374761472 |
|---|---|
| author | Zhang, Wei Wu, Yihang Li, Songhua Ma, Wenjie Ma, Xin Li, Qiang Wang, Qi |
| author_facet | Zhang, Wei Wu, Yihang Li, Songhua Ma, Wenjie Ma, Xin Li, Qiang Wang, Qi |
| contents | 3D reconstruction, which aims to recover the dense three-dimensional structure of a scene, is a cornerstone technology for numerous applications, including augmented/virtual reality, autonomous driving, and robotics. While traditional pipelines like Structure from Motion (SfM) and Multi-View Stereo (MVS) achieve high precision through iterative optimization, they are limited by complex workflows, high computational cost, and poor robustness in challenging scenarios like texture-less regions. Recently, deep learning has catalyzed a paradigm shift in 3D reconstruction. A new family of models, exemplified by DUSt3R, has pioneered a feed-forward approach. These models employ a unified deep network to jointly infer camera poses and dense geometry directly from an Unconstrained set of images in a single forward pass. This survey provides a systematic review of this emerging domain. We begin by dissecting the technical framework of these feed-forward models, including their Transformer-based correspondence modeling, joint pose and geometry regression mechanisms, and strategies for scaling from two-view to multi-view scenarios. To highlight the disruptive nature of this new paradigm, we contrast it with both traditional pipelines and earlier learning-based methods like MVSNet. Furthermore, we provide an overview of relevant datasets and evaluation metrics. Finally, we discuss the technology's broad application prospects and identify key future challenges and opportunities, such as model accuracy and scalability, and handling dynamic scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08448 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT Zhang, Wei Wu, Yihang Li, Songhua Ma, Wenjie Ma, Xin Li, Qiang Wang, Qi Computer Vision and Pattern Recognition Artificial Intelligence 3D reconstruction, which aims to recover the dense three-dimensional structure of a scene, is a cornerstone technology for numerous applications, including augmented/virtual reality, autonomous driving, and robotics. While traditional pipelines like Structure from Motion (SfM) and Multi-View Stereo (MVS) achieve high precision through iterative optimization, they are limited by complex workflows, high computational cost, and poor robustness in challenging scenarios like texture-less regions. Recently, deep learning has catalyzed a paradigm shift in 3D reconstruction. A new family of models, exemplified by DUSt3R, has pioneered a feed-forward approach. These models employ a unified deep network to jointly infer camera poses and dense geometry directly from an Unconstrained set of images in a single forward pass. This survey provides a systematic review of this emerging domain. We begin by dissecting the technical framework of these feed-forward models, including their Transformer-based correspondence modeling, joint pose and geometry regression mechanisms, and strategies for scaling from two-view to multi-view scenarios. To highlight the disruptive nature of this new paradigm, we contrast it with both traditional pipelines and earlier learning-based methods like MVSNet. Furthermore, we provide an overview of relevant datasets and evaluation metrics. Finally, we discuss the technology's broad application prospects and identify key future challenges and opportunities, such as model accuracy and scalability, and handling dynamic scenes. |
| title | Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.08448 |