The University of Tokyo * Corresponding Author
In European Conference on Computer Vision (ECCV) 2024
Stay tuned. Feel free to contact me for bugs or missing files.
conda create -n rsnerf python==3.10
conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cudatoolkit=11.3 -c pytorch
pip install -r requirements.txt
We contribute synthetic and real datasets for evaluating RS-related novel-view synthesis techniques that follows the forward-facing manner.
Download the synthetic and real dataset from this link and unzip them to the current directory.
Download the pretrained RAFT model (raft-things.pth) from this link and unzip it to ./raft_models.
python train.py \
--config configs/wine.txt
python train_real.py \
--config configs/real_toy.txt
We appreciate for nerf-pytorch and BAD-NeRF, upon which we build our code implementation. We would also appreciate the code release of USB-NeRF, rspy, JAMNet, CVR, and DeepUnroll for comparison and evaluation.