Skip to content


Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?

NeRD: Neural Reflectance Decomposition from Image Collections

Project Page | Video | Paper | Dataset

Implementation for NeRD. A novel method which decomposes multiple images into shape, BRDF and illumination.

NeRD: Neural Reflectance Decomposition from Image Collections
Mark Boss1, Raphael Braun1, Varun Jampani2, Jonathan T. Barron2, Ce Liu2, Hendrik P. A. Lensch1
1University of Tübingen, 2Google Research

Also check our follow-up work: Neural-PIL


A conda environment is used for dependency management

conda env create -f environment.yml
conda activate nerd


Replace the specific [] placeholders:

python --datadir [DIR_TO_DATASET_FOLDER] --basedir [TRAIN_DIR] --expname [EXPERIMENT_NAME] --gpu [COMMA_SEPARATED_GPU_LIST]

Specific Arguments per Dataset

Most setup is handled by configurations files located in configs/nerd/.

Our Synthethic Scenes

--config configs/nerd/blender.txt

NeRF Synthethic Scenes

--config configs/nerd/nerf_blender.txt


--config configs/nerd/real_world.txt 

Often objects are captured in a spherical manner and the flag --spherify should be applied for those scenes.


All datasets are uploaded in individual git repositories. We have created a download script which automatically fetches all datasets and downloads them to a specified folder. Usage:

python /path/to/dataset/root

Run Your Own Data

Mainly camera poses and segmentation masks are required. For the poses the scripts from NeRF are used to prepare the scenes. The dataset then needs to be put in the following file structure:


The poses_bounds.npy is generated from the LLFF script.


The can be called with a --render_only flag and the --config flag pointing to the args.txt of the experiments folder. The SGs can be converted to regular environment maps with the visualize_fit function in nn_utils/ (Example in


  title         = {NeRD: Neural Reflectance Decomposition from Image Collections},
  author        = {Boss, Mark and Braun, Raphael and Jampani, Varun and Barron, Jonathan T. and Liu, Ce and Lensch, Hendrik P.A.},
  booktitle     = {IEEE International Conference on Computer Vision (ICCV)},
  year          = {2021},