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

arXiv: https://arxiv.org/abs/2604.02785 · HTML: https://mlsanity.com/paper/2604.02785/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [ReZero is All You Need: Fast Convergence at Large Depth](https://mlsanity.com/paper/2003.04887/) (2020)
- [Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement](https://mlsanity.com/paper/2303.06705/) (2023)
- [Multi-level Wavelet-CNN for Image Restoration](https://mlsanity.com/paper/1805.07071/) (2018)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2212.04711/) (2022)
- [Shadow Removal via Shadow Image Decomposition](https://mlsanity.com/paper/1908.08628/) (2019)
- [Frequency-aware Feature Fusion for Dense Image Prediction](https://mlsanity.com/paper/2408.12879/) (2024)
- [DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity](https://mlsanity.com/paper/2211.08089/) (2022)
- [Latent Feature-Guided Diffusion Models for Shadow Removal](https://mlsanity.com/paper/2312.02156/) (2023)
- [OmniSR: Shadow Removal under Direct and Indirect Lighting](https://mlsanity.com/paper/2410.01719/) (2024)
- [Detail-Preserving Latent Diffusion for Stable Shadow Removal](https://mlsanity.com/paper/2412.17630/) (2024)
- [Regional Attention for Shadow Removal](https://mlsanity.com/paper/2411.14201/) (2024)
- [Towards Image Ambient Lighting Normalization](https://mlsanity.com/paper/2403.18730/) (2024)
- [DenseSR: Image Shadow Removal as Dense Prediction](https://mlsanity.com/paper/2507.16472/) (2025)
- [After the Party: Navigating the Mapping From Color to Ambient Lighting](https://mlsanity.com/paper/2508.02168/) (2025)
- [PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors](https://mlsanity.com/paper/2601.17470/) (2026)
- [WWE-UIE: A Wavelet & White Balance Efficient Network for Underwater Image Enhancement](https://mlsanity.com/paper/2511.16321/) (2025)
- [ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation](https://mlsanity.com/paper/2601.17468/) (2026)

## Abstract (arXiv)

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.