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

:::info 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.

:::

:::tip 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.

:::

• Abstract and 1. Introduction
• 2. Related Work
• 3. SwitchLight and 3.1. Preliminaries
• 3.2. Problem Formulation
• 3.3. Architecture
• 3.4. Objectives
• 4. Multi-Masked Autoencoder Pre-training
• 5. Data
• 6. Experiments
• 7. Conclusion

\ Appendix

• A. Implementation Details
• B. User Study Interface
• C. Video Demonstration
• D. Additional Qualitative Results & References

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.

\

\

\

\ 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.

\

\

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

:::

\