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

Source: [CANDLE: Illumination-Invariant Semantic Priors for Color Ambient Lighting Normalization](<https://www.sota2.com/research/paper/69d33dda7d0172140ec734fb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-07T05:00:04.607Z

Authors: Rong-Lin Jian, Ting-Yao Chen, Yu-Fan Lin, Chia-Ming Lee, Fu-En Yang, Yu-Chiang Frank Wang, Chih-Chung Hsu

Published: 2026-04-03T06:49:53.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Ambient Lighting Normalization on CL3AN (test)](<https://www.sota2.com/research/sota/ambient-lighting-normalization-on-cl3an-test.md>): Ambient Lighting Normalization; CL3AN (test); PSNR: 21.066.

- [Ambient Lighting Normalization on NTIRE ALN Color Lighting Challenge 2026](<https://www.sota2.com/research/sota/ambient-lighting-normalization-on-ntire-aln-color-lighting-challenge-2026.md>): Ambient Lighting Normalization; NTIRE ALN Color Lighting Challenge 2026; PSNR: 21.432.

- [Ambient Lighting Normalization on NTIRE ALN White Lighting Challenge 2026 (official leaderboard)](<https://www.sota2.com/research/sota/ambient-lighting-normalization-on-ntire-aln-white-lighting-challenge-2026-official-leaderboard.md>): Ambient Lighting Normalization; NTIRE ALN White Lighting Challenge 2026 (official leaderboard); PSNR: 24.875.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.02785>)

[PDF](<https://arxiv.org/pdf/2604.02785.pdf>)
