Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915687524466688 |
|---|---|
| author | Zhang, Jiahui Li, Yuelei Chen, Anpei Xu, Muyu Liu, Kunhao Wang, Jianyuan Long, Xiao-Xiao Liang, Hanxue Xu, Zexiang Su, Hao Theobalt, Christian Rupprecht, Christian Vedaldi, Andrea Zhou, Kaichen Pfister, Hanspeter Liang, Paul Pu Lu, Shijian Zhan, Fangneng |
| author_facet | Zhang, Jiahui Li, Yuelei Chen, Anpei Xu, Muyu Liu, Kunhao Wang, Jianyuan Long, Xiao-Xiao Liang, Hanxue Xu, Zexiang Su, Hao Theobalt, Christian Rupprecht, Christian Vedaldi, Andrea Zhou, Kaichen Pfister, Hanspeter Liang, Paul Pu Lu, Shijian Zhan, Fangneng |
| contents | 3D reconstruction and view synthesis are foundational problems in computer vision, graphics, and immersive technologies such as augmented reality (AR), virtual reality (VR), and digital twins. Traditional methods rely on computationally intensive iterative optimization in a complex chain, limiting their applicability in real-world scenarios. Recent advances in feed-forward approaches, driven by deep learning, have revolutionized this field by enabling fast and generalizable 3D reconstruction and view synthesis. This survey offers a comprehensive review of feed-forward techniques for 3D reconstruction and view synthesis, with a taxonomy according to the underlying representation architectures including point cloud, 3D Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), etc. We examine key tasks such as pose-free reconstruction, dynamic 3D reconstruction, and 3D-aware image and video synthesis, highlighting their applications in digital humans, SLAM, robotics, and beyond. In addition, we review commonly used datasets with detailed statistics, along with evaluation protocols for various downstream tasks. We conclude by discussing open research challenges and promising directions for future work, emphasizing the potential of feed-forward approaches to advance the state of the art in 3D vision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14501 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey Zhang, Jiahui Li, Yuelei Chen, Anpei Xu, Muyu Liu, Kunhao Wang, Jianyuan Long, Xiao-Xiao Liang, Hanxue Xu, Zexiang Su, Hao Theobalt, Christian Rupprecht, Christian Vedaldi, Andrea Zhou, Kaichen Pfister, Hanspeter Liang, Paul Pu Lu, Shijian Zhan, Fangneng Computer Vision and Pattern Recognition 3D reconstruction and view synthesis are foundational problems in computer vision, graphics, and immersive technologies such as augmented reality (AR), virtual reality (VR), and digital twins. Traditional methods rely on computationally intensive iterative optimization in a complex chain, limiting their applicability in real-world scenarios. Recent advances in feed-forward approaches, driven by deep learning, have revolutionized this field by enabling fast and generalizable 3D reconstruction and view synthesis. This survey offers a comprehensive review of feed-forward techniques for 3D reconstruction and view synthesis, with a taxonomy according to the underlying representation architectures including point cloud, 3D Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), etc. We examine key tasks such as pose-free reconstruction, dynamic 3D reconstruction, and 3D-aware image and video synthesis, highlighting their applications in digital humans, SLAM, robotics, and beyond. In addition, we review commonly used datasets with detailed statistics, along with evaluation protocols for various downstream tasks. We conclude by discussing open research challenges and promising directions for future work, emphasizing the potential of feed-forward approaches to advance the state of the art in 3D vision. |
| title | Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.14501 |