CANDLE: Illumination-Invariant Semantic Priors for Color Ambient Lighting Normalization

Abstract

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.

Figures (5)

• Figure 1: DINOv3 dinov3 features remain highly consistent under colored illumination. Despite severe appearance shifts between the colored-light input and the ambient-lit GT, DINOv3 PCA visualizations remain highly consistent across domains. Patch-wise cosine similarity maps (brighter $=$ stronger consistency) show that DINOv3 preserves substantially higher similarity both on average ($P$) and in the hardest regions ($W$), outperforming CLIP clip and supervised ResNet-50 he2016resnet.
• Figure 2: Quantitative representation consistency over 10 input/GT pairs. DINOv3 dinov3 achieves the highest average patch-wise cosine similarity and the strongest robustness on the hardest 10% of regions ($W$), consistently outperforming CLIP clip and ResNet-50 he2016resnet.
• Figure 3: Overview of CANDLE. Multi-layer features from a frozen DINOv3 dinov3 ViT-L/16 are adaptively selected and fused via PSF and injected into successive encoder stages through DRFB (D.O.G., Sec. \ref{['sec:dog']}), replacing surface-normal guidance with illumination-robust semantic priors. At the decoder, BFACG decouples structural and chromatic restoration under edge-aware modulation, while SFFB suppresses illumination-corrupted skip features via Haar wavelet gating (Sec. \ref{['sec:cfr']}).
• Figure 4: Qualitative comparison with state-of-the-art methods on CL3AN cl3an. General restoration methods nafnetrestormer exhibit washed-out colors and incomplete correction under strong chromatic shifts. ALN-specific methods ambient6kpromptnorm partially recover global color balance but remain inconsistent across materials, as frequency and geometric priors are insufficient when chromaticity shifts dominate. CANDLE recovers object-intrinsic color more faithfully with sharper boundaries, enabled by D.O.G. and color-frequency refinement.
• Figure 5: Training dynamics of ablation variants. (a) D.O.G. sustains a peak gain of +3.68 dB over the unguided baseline, with the gap maintained across all training epochs, confirming a structural rather than incidental improvement. (b) Query-based fusion converges more stably than input-concat or value-fusion variants in later epochs.