TokenLight encodes lighting attributes as tokens in a conditional image generation model trained mostly on synthetic data, enabling precise relighting control and implicit learning of light-scene interactions.
Gomez, Łukasz Kaiser, and Il- lia Polosukhin
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LSENet adds PIE patch attention, MFF multi-scale fusion, and CRD refinement to U-Net for OCTA vessel segmentation, claiming SOTA results on three public datasets with fewer parameters.
citing papers explorer
-
TokenLight: Precise Lighting Control in Images using Attribute Tokens
TokenLight encodes lighting attributes as tokens in a conditional image generation model trained mostly on synthetic data, enabling precise relighting control and implicit learning of light-scene interactions.
-
Gaze into the Details: Locality-Sensitive Enhancement for OCTA Retinal Vessel Segmentation
LSENet adds PIE patch attention, MFF multi-scale fusion, and CRD refinement to U-Net for OCTA vessel segmentation, claiming SOTA results on three public datasets with fewer parameters.