Yağız Aksoy

Has grant

Assistant Professor

Simon Fraser University
Country flagCanada

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

About

Yağız Aksoy is an Assistant Professor at Simon Fraser University in Canada. His research primarily focuses on intrinsic image decomposition and related areas, as highlighted in his recent publications, including "Colorful Diffuse Intrinsic Image Decomposition in the Wild" and "Intrinsic Image Decomposition via Ordinal Shading." He is dedicated to advancing the understanding of image processing techniques within the field of computer vision.

Recent Grants

Grant: Close

Image Analysis for Realistic Scene Manipulation

Open Date: 2021-04-01

Close Date: 2022-03-31

Grant: Close

Computational Cinematography

Open Date: 2021-01-01

Close Date:

Articles (7)

Year:

2025

Year:

2025

Year:

2025

Year:

2025

Year:

2025

Year:

2024

Intrinsic decomposition is a fundamental mid-level vision problem that plays a crucial role in various inverse rendering and computational photography pipelines. Generating highly accurate intrinsic decompositions is an inherently under-constrained task that requires precisely estimating continuous-valued shading and albedo. In this work, we achieve high-resolution intrinsic decomposition by breaking the problem into two parts. First, we present a dense ordinal shading formulation using a shift- and scale-invariant loss in order to estimate ordinal shading cues without restricting the predictions to obey the intrinsic model. We then combine low- and high-resolution ordinal estimations using a second network to generate a shading estimate with both global coherency and local details. 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. We develop a straightforward method for generating dense pseudo ground truth using our model’s predictions and multi-illumination data, enabling generalization to in-the-wild imagery. We present exhaustive qualitative and quantitative analysis of our predicted intrinsic components against state-of-the-art methods. Finally, we demonstrate the real-world applicability of our estimations by performing otherwise difficult editing tasks such as recoloring and relighting.

Year:

2023