EUVIMEDEUVIMED entdecken
Crossref

Advances in Feed‐Forward 3D Reconstruction and View Synthesis: A Survey

Jiahui Zhang, Yuelei Li, Anpei Chen, Muyu Xu, Kunhao Liu, Jianyuan Wang, Xiao‐Xiao Long, Hanxue Liang, Zexiang Xu, Hao Su, Christian Theobalt, Christian Rupprecht und 6 weitere

Computer Graphics Forum · 06.05.2026

DOI: 10.1111/cgf.70494 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 06.05.2026. Verfasst von Jiahui Zhang und 17 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 330 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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. The project page is available at https://fnzhan.com/projects/Feed‐Forward‐3D Feed‐Forward‐3D.

Zitieren

APA

Zhang, J., Li, Y., Chen, A., Xu, M., Liu, K., Wang, J., Long, X., Liang, H., Xu, Z., Su, H., Theobalt, C., Rupprecht, C., Vedaldi, A., Zhou, K., Pfister, H., Liang, P. P., Lu, S., & Zhan, F. (2026). Advances in Feed‐Forward 3D Reconstruction and View Synthesis: A Survey. Computer Graphics Forum. https://doi.org/10.1111/cgf.70494

Vancouver

Zhang J, Li Y, Chen A, Xu M, Liu K, Wang J, et al. Advances in Feed‐Forward 3D Reconstruction and View Synthesis: A Survey. Computer Graphics Forum. 2026. doi:10.1111/cgf.70494

BibTeX
@article{Zhang2026,
  author = {Zhang, Jiahui and Li, Yuelei and Chen, Anpei and Xu, Muyu and Liu, Kunhao and Wang, Jianyuan and Long, Xiao‐Xiao and Liang, Hanxue and Xu, Zexiang and Su, Hao and Theobalt, Christian and Rupprecht, Christian and Vedaldi, Andrea and Zhou, Kaichen and Pfister, Hanspeter and Liang, Paul Pu and Lu, Shijian and Zhan, Fangneng},
  title = {Advances in Feed‐Forward 3D Reconstruction and View Synthesis: A Survey},
  journal = {Computer Graphics Forum},
  year = {2026},
  doi = {10.1111/cgf.70494}
}
Kostenlos starten →