Loading...

Advances in Feed-Forward 3D Reconstruction
and View Synthesis

Jiahui Zhang*1Yuelei Li*2Anpei Chen3,9Muyu Xu1Kunhao Liu1Jianyuan Wang4Xiao-Xiao Long5,6
Hanxue Liang7Zexiang Xu8Hao Su9Christian Theobalt10Christian Rupprecht4
Andrea Vedaldi4Kaichen Zhou11,12Paul Pu Liang12Shijian Lu1Fangneng Zhan12,11

1NTU, 2Caltech, 3Westlake University, 4University of Oxford, 5Nanjing University, 6HKU,
7University of Cambridge, 8Hillbot, 9UCSD, 10MPI-INF, 11Harvard University, 12MIT

* denotes equal contribution.


missing
Paper
missing

Abstract

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.

Summary

missing
A summary of the representative works
          
missing
A summary of popular datasets

Methods


1. NeRF-based Methods

missing



2. Pointmap-based Methods

missing



3. 3DGS-based Methods



missing



4. Representation-free Methods

missing
Regression-based methods


missing
Generative methods
Top