vincentfung13/MINE
PyTorch implementation of MINE, a NeRF-based method for reconstructing 3D scenes from single images and synthesizing novel camera views.
Not currently ranked — collecting fresh signals.
star history
This repository contains the code and models for an ICCV 2021 paper that uses neural radiance fields combined with multi-plane images (MPI) to perform novel view synthesis from a single input image. The method reconstructs a continuous depth frustum of the camera, enabling efficient rendering of novel viewpoints. It is trained on datasets including LLFF, RealEstate10K, and KITTI Raw using PyTorch and tensorboard for logging.
Frequently asked
- What is vincentfung13/MINE?
- PyTorch implementation of MINE, a NeRF-based method for reconstructing 3D scenes from single images and synthesizing novel camera views.
- Is MINE open source?
- Yes — vincentfung13/MINE is open source, released under the MIT license.
- What language is MINE written in?
- vincentfung13/MINE is primarily written in Python.
- How popular is MINE?
- vincentfung13/MINE has 423 stars on GitHub.
- Where can I find MINE?
- vincentfung13/MINE is on GitHub at https://github.com/vincentfung13/MINE.