Intrinsic Harmonization for Illumination-Aware Compositing

1 code implementation • 6 Dec 2023 • Chris Careaga, S. Mahdi H. Miangoleh, Yağız Aksoy

Despite significant advancements in network-based image harmonization techniques, there still exists a domain disparity between typical training pairs and real-world composites encountered during inference.

Image Harmonization Image Relighting

Intrinsic Image Decomposition via Ordinal Shading

2 code implementations • ACM Transactions on Graphics 2023 • Chris Careaga, Yağız Aksoy

We encourage the model to learn an accurate decomposition by computing losses on the estimated shading as well as the albedo implied by the intrinsic model.

Intrinsic Image Decomposition Inverse Rendering

Realistic Saliency Guided Image Enhancement

1 code implementation • CVPR 2023 • S. Mahdi H. Miangoleh, Zoya Bylinskii, Eric Kee, Eli Shechtman, Yağız Aksoy

We thus offer a viable solution for automating image enhancement and photo cleanup operations.

Image Enhancement

Computational Flash Photography through Intrinsics

no code implementations • CVPR 2023 • Sepideh Sarajian Maralan, Chris Careaga, Yağız Aksoy

Flash is an essential tool as it often serves as the sole controllable light source in everyday photography.

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

1 code implementation • CVPR 2021 • S. Mahdi H. Miangoleh, Sebastian Dille, Long Mai, Sylvain Paris, Yağız Aksoy

Neural networks have shown great abilities in estimating depth from a single image.

Monocular Depth Estimation

Information-Flow Matting

1 code implementation • CVPR 2017 • Yağız Aksoy, Tunç Ozan Aydın, Marc Pollefeys

Our resulting novel linear system formulation can be solved in closed-form and is robust against several fundamental challenges of natural matting such as holes and remote intricate structures.

Image Matting