TokenLight: Precise Lighting Control in Images using Attribute Tokens

arXiv cs.CV / 4/17/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

TokenLight is a new image relighting approach that treats relighting as conditional image generation with fine-grained, continuous control over multiple lighting attributes.
The method introduces “attribute tokens” to represent distinct illumination factors (e.g., intensity, color, ambient and diffuse levels, and 3D light positions) for targeted editing.
Training combines a large synthetic dataset with ground-truth lighting annotations and a small set of real captures to improve realism and generalization.
Experiments across both synthetic and real images show state-of-the-art results for tasks such as controlling in-scene fixtures and using virtual lights to edit environment illumination.
Notably, the model learns light–scene interactions (geometry, occlusion, and materials) without explicit inverse-rendering supervision, producing plausible relighting even for difficult cases like lights placed inside objects or transparent materials.

Abstract

This paper presents a method for image relighting that enables precise and continuous control over multiple illumination attributes in a photograph. We formulate relighting as a conditional image generation task and introduce attribute tokens to encode distinct lighting factors such as intensity, color, ambient illumination, diffuse level, and 3D light positions. The model is trained on a large-scale synthetic dataset with ground-truth lighting annotations, supplemented by a small set of real captures to enhance realism and generalization. We validate our approach across a variety of relighting tasks, including controlling in-scene lighting fixtures and editing environment illumination using virtual light sources, on synthetic and real images. Our method achieves state-of-the-art quantitative and qualitative performance compared to prior work. Remarkably, without explicit inverse rendering supervision, the model exhibits an inherent understanding of how light interacts with scene geometry, occlusion, and materials, yielding convincing lighting effects even in traditionally challenging scenarios such as placing lights within objects or relighting transparent materials plausibly. Project page: vrroom.github.io/tokenlight/