/SIRe-IR

Official implementation of "SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes"

SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes

Project page (Coming Soon...) | Paper | Synthetic Data | Real Data

This repository contains the official implementation associated with the paper "SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes". We will release our code after we sort it out.

Preparation

  • Set up the Python environment
conda create -n sire-env python=3.7
conda activate sire-env

pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116
pip install pyg-lib torch-scatter torch-sparse torch-cluster torch-spline-conv torch-geometric -f https://data.pyg.org/whl/torch-1.13.0+cu116.html
pip install -r requirement.txt

Results

Albedo

image-20231020012659356

Roughness

image-20231020012659356

Envmap

image-20231020012659356

Relighting

image-20231020012659356

De-shadow

image-20231020012659356

BibTex

@article{yang2023sireir,
    title={SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes},
    author={Yang, Ziyi and Chen, Yanzhen and Gao, Xinyu and Yuan, Yazhen and Wu, Yu and Zhou, Xiaowei and Jin, Xiaogang},
    journal={arXiv preprint arXiv:2310.13030},
    year={2023}
}