[AAAI25 Oral] DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation

• 2025.4.23: DiffCalib has been published at Proceedings of the AAAI Conference on Artificial Intelligence.
• 2025.2.15: Congratulations! DiffCalib has been accepted as an oral presentation at AAAI 2025. AAAI 2025 received a total of 12,957 valid submissions, with 3,032 papers accepted, resulting in an acceptance rate of 23.4%. Among these, Oral papers accounted for 4.6%.
• 2024.7.25: Release inference code and checkpoint weight of Diffcalib in the repo.
• 2024.7.25: Release arXiv paper, with supplementary material.

conda create -n diffcalib python=3.10
conda activate diffcalib
pip install -r requirements.txt
pip install -e .

Download the intrinsic data from MonoCalib

First, Download the stable-diffusion-2-1 and transform it to the 8 inchannels from modify which will be put in --checkpoint, put the checkpoints under ./checkpoint/

Then, Download the pre-trained models diffcalib-best.zip from BaiduNetDisk(Extract code：xn5p). Please unzip the package and put the checkpoints under ./checkpoint/ which will be put in --unet_ckpt_path.

finally, you can run the bash to evaluate our model in the benchmark.

sh scripts/run_incidence_mutidata.sh

For depth and incident map visualization , download shift model from res101 (Extract code: g3yi), diffcalib-pcd.zip from BaiduNetDisk(Extract code:20z6) and install torchsparse packages as follows

sudo apt-get install libsparsehash-dev
pip install --upgrade git+https://github.com/mit-han-lab/torchsparse.git@v1.2.0

Then we can reconstruct 3D shape from a single image.

bash scripts/run_incidence_depth_pcd.sh

• Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation. arXiv, GitHub.

For non-commercial use, this code is released under the LICENSE.

@article{
	He_Xu_Zhang_Chen_Cui_Guo_2025, 
	title={DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation}, 
	volume={39},
	DOI={10.1609/aaai.v39i3.32355},  
	number={3},
	journal={Proceedings of the AAAI Conference on Artificial Intelligence}, 
	author={He, Xiankang and Xu, Guangkai and Zhang, Bo and Chen, Hao and Cui, Ying and Guo, Dongyan}, 
	year={2025}, 
	month={Apr.}, 
	pages={3428-3436}
}