Beeble Researchers Develop AI That Can Make Any Photo Look Perfectly Lit—Even in the Darkest Room by@autoencoder
119 reads
Beeble Researchers Develop AI That Can Make Any Photo Look Perfectly Lit—Even in the Darkest Room
by Auto Encoder: How to Ignore the Signal NoiseDecember 21st, 2024
Auto Encoder: How to Ignore the Signal Noise
@autoencoder
Research & publications on Auto Encoders, revolutionizing data compression and...
Read this story in a terminal
Print this story
Read this story w/o Javascript
Too Long; Didn't Read
Researchers at Beeble AI have developed a method for improving how light and shadows can be applied to human portraits in digital images.
1x
Read by Dr. One
Listen to this story
Auto Encoder: How to Ignore the Signal Noise
@autoencoder
Research & publications on Auto Encoders, revolutionizing data compression and feature learning techniques.
Learn More
LEARN MORE ABOUT @AUTOENCODER'S
EXPERTISE AND PLACE ON THE INTERNET.
EXPERTISE AND PLACE ON THE INTERNET.
STORY’S CREDIBILITY
Academic Research Paper
Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.
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.
Table of Links
- 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
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.
L O A D I N G
. . . comments & more!
. . . comments & more!
