DreamLight: Towards Harmonious and Consistent Image Relighting
Yong Liu, Wenpeng Xiao, Qianqian Wang, Junlin Chen, Shiyin Wang, Yitong Wang, Xinglong Wu, Yansong Tang

TL;DR
DreamLight is a universal image relighting model that seamlessly composites subjects into new backgrounds, maintaining aesthetic lighting and color consistency, and supports both image-based and text-based background specification.
Contribution
The paper introduces a novel unified framework with a Position-Guided Light Adapter and Spectral Foreground Fixer for realistic, natural relighting in both image and text-guided scenarios.
Findings
Achieves superior relighting quality in experiments.
Effectively handles both image-based and text-based background inputs.
User studies confirm high satisfaction with results.
Abstract
We introduce a model named DreamLight for universal image relighting in this work, which can seamlessly composite subjects into a new background while maintaining aesthetic uniformity in terms of lighting and color tone. The background can be specified by natural images (image-based relighting) or generated from unlimited text prompts (text-based relighting). Existing studies primarily focus on image-based relighting, while with scant exploration into text-based scenarios. Some works employ intricate disentanglement pipeline designs relying on environment maps to provide relevant information, which grapples with the expensive data cost required for intrinsic decomposition and light source. Other methods take this task as an image translation problem and perform pixel-level transformation with autoencoder architecture. While these methods have achieved decent harmonization effects, they…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputer Graphics and Visualization Techniques · Data Visualization and Analytics · Video Analysis and Summarization
MethodsDiffusion · Adapter · Focus
