Beeble Researchers Develop AI That Can Make Any Photo Look Perfectly Lit—Even in the Darkest Room

cover
21 Dec 2024

Authors:

(1) Hoon Kim, Beeble AI, and contributed equally to this work;

(2) Minje Jang, Beeble AI, and contributed equally to this work;

(3) Wonjun Yoon, Beeble AI, and contributed equally to this work;

(4) Jisoo Lee, Beeble AI, and contributed equally to this work;

(5) Donghyun Na, Beeble AI, and contributed equally to this work;

(6) Sanghyun Woo, New York University, and contributed equally to this work.

Editor's Note: This is Part 6 of 14 of a study introducing a method for improving how light and shadows can be applied to human portraits in digital images. Read the rest below.

Appendix

3.4. Objectives

We supervise both intrinsic image attributes and relit images using their corresponding ground truths, obtained from the lightstage. We employ a combination of reconstruction, perceptual [24], adversarial [22], and specular [34] losses.

Figure 4. Neural Render Enhancement. Using the CookTorrance model, diffuse and specular renders are computed, which are then composited into a physically-based rendering. Subsequently, a neural network enhances this PBR render, improving aspects such as brightness and specular details.

Final Loss. The SwitchLight is trained in an end-to-end manner using the weighted sum of the above losses:

We empirically determined the weighting coefficients.

Figure 5. Dynamic Masking Strategies. We have generalized the MAE masks to include overlapping patches of varying sizes, as well as outpainting and free-form masks.

This paper is available on arxiv under CC BY-NC-SA 4.0 DEED license.