MatchNeRF

This repository serves as a storage space for the pre-trained weights and selected preprocessed datasets used in MatchNeRF.

Explicit Correspondence Matching for Generalizable Neural Radiance Fields
Yuedong Chen¹, Haofei Xu², Qianyi Wu¹, Chuanxia Zheng³, Tat-Jen Cham⁴, Jianfei Cai^1
1Monash University, ²ETH Zurich, ³University of Oxford, ⁴Nanyang Technological University
TPAMI 2025

Paper | Project Page | Code | Model

Contents

Pre-trained weights

• gmflow_sintel-0c07dcb3.pth: Pre-trained weights for GMFlow, used to initialize our backbone when training, provided as a backup of the original available on Google Drive.
• matchnerf_3v.pth: Pre-trained weights for MatchNeRF using DTU dataset, trained using 3 input views. Used for benchmarks testing.
• matchnerf_3v_ibr.pth: Pre-trained weights for MatchNeRF using IBRNet datasets, trained using 3 input views. More suitable for in-the-wild scenes.

Datasets

• nerf_synthetic.zip: Blender dataset, provided as a backup of the original available on Google Drive.
• nerf_llff_data.zip: Real Forward Facing dataset, provided as a backup of the original available on Google Drive.
• tnt_data.zip: Tanks and Temples dataset, provided as a backup of the original available on Google Drive.

Acknowledgement

This repository contains data that has been derived from publicly available open-source resources. All rights and credit for the original data go to the respective creators and contributors of those projects.

If you are the owner of any content included in this repository and believe that its inclusion violates your rights or licensing terms, please contact me ("donny") via donny[DOT]chen[AT]outlook[DOT]sg. Upon receipt of a valid request, we will promptly take appropriate action, which may include the removal of the content in question.

BibTex

If you use this project for your research, please cite our paper.

@article{chen2025explicit,
  title={Explicit correspondence matching for generalizable neural radiance fields},
  author={Chen, Yuedong and Xu, Haofei and Wu, Qianyi and Zheng, Chuanxia and Cham, Tat-Jen and Cai, Jianfei},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2025},
  publisher={IEEE}
}