CANDLE: Illumination-Invariant Semantic Priors for Color Ambient Lighting Normalization
This addresses color normalization for computer vision applications under challenging lighting, but it is incremental as it builds on existing self-supervised features.
The paper tackles the problem of color ambient lighting normalization under multi-colored illumination, which suffers from chromatic shifts and highlight saturation, by using DINOv3's self-supervised features as illumination-robust semantic priors. It achieves a +1.22 dB PSNR gain over prior methods and strong performance in challenge benchmarks.
Color ambient lighting normalization under multi-colored illumination is challenging due to severe chromatic shifts, highlight saturation, and material-dependent reflectance. Existing geometric and low-level priors are insufficient for recovering object-intrinsic color when illumination-induced chromatic bias dominates. We observe that DINOv3's self-supervised features remain highly consistent between colored-light inputs and ambient-lit ground truth, motivating their use as illumination-robust semantic priors. We propose CANDLE (Color Ambient Normalization with DINO Layer Enhancement), which introduces DINO Omni-layer Guidance (D.O.G.) to adaptively inject multi-layer DINOv3 features into successive encoder stages, and a color-frequency refinement design (BFACG + SFFB) to suppress decoder-side chromatic collapse and detail contamination. Experiments on CL3AN show a +1.22 dB PSNR gain over the strongest prior method. CANDLE achieves 3rd place on the NTIRE 2026 ALN Color Lighting Challenge and 2nd place in fidelity on the White Lighting track with the lowest FID, confirming strong generalization across both chromatic and luminance-dominant illumination conditions. Code is available at https://github.com/ron941/CANDLE.