Pith. sign in

REVIEW 12 cited by

Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.11831 v1 pith:SJT235GV submitted 2023-02-23 cs.CV

Chongyi Li , Chun-Le Guo , Man Zhou , Zhexin Liang , Shangchen Zhou , Ruicheng Feng , Chen Change Loy This is my paper · ORCID
classification cs.CV
keywords imagedatasetenhancementfourierllienoiseamplitudeexisting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Ultra-High-Definition (UHD) photo has gradually become the standard configuration in advanced imaging devices. The new standard unveils many issues in existing approaches for low-light image enhancement (LLIE), especially in dealing with the intricate issue of joint luminance enhancement and noise removal while remaining efficient. Unlike existing methods that address the problem in the spatial domain, we propose a new solution, UHDFour, that embeds Fourier transform into a cascaded network. Our approach is motivated by a few unique characteristics in the Fourier domain: 1) most luminance information concentrates on amplitudes while noise is closely related to phases, and 2) a high-resolution image and its low-resolution version share similar amplitude patterns.Through embedding Fourier into our network, the amplitude and phase of a low-light image are separately processed to avoid amplifying noise when enhancing luminance. Besides, UHDFour is scalable to UHD images by implementing amplitude and phase enhancement under the low-resolution regime and then adjusting the high-resolution scale with few computations. We also contribute the first real UHD LLIE dataset, \textbf{UHD-LL}, that contains 2,150 low-noise/normal-clear 4K image pairs with diverse darkness and noise levels captured in different scenarios. With this dataset, we systematically analyze the performance of existing LLIE methods for processing UHD images and demonstrate the advantage of our solution. We believe our new framework, coupled with the dataset, would push the frontier of LLIE towards UHD. The code and dataset are available at https://li-chongyi.github.io/UHDFour.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes

    cs.CV 2026-01 unverdicted novelty 7.0 of 10

    RL-AWB uses reinforcement learning to optimize parameters of a statistical white-balance estimator for nighttime scenes and reports better generalization on a new multi-sensor dataset.

  2. MoCRA: Mixture of Compositional Rank-1 Atoms for 4K All-in-One Video Restoration

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A single 3.6M-parameter model, MoCRA, restores haze, rain, noise, and low light at native 4K in 0.48 seconds per frame, besting eleven retrained baselines on the mean PSNR of the authors' new UHV-4K-AIO benchmark.

  3. UNICE: Training A Universal Image Contrast Enhancer

    cs.CV 2025-07 conditional novelty 6.0 of 10

    UNICE trains a two-stage model to generate and fuse a pseudo multi-exposure sequence from one image, generalizing across four contrast-enhancement tasks without human labels.

  4. Wavelet-based Decoupling Framework for low-light Stereo Image Enhancement

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A wavelet-based decoupling network for low-light stereo enhancement, using a low-frequency branch for illumination and high-frequency branches for texture with cross-view interaction, reports state-of-the-art PSNR/SSI...

  5. UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache

    cs.CV 2025-05 reject novelty 6.0 of 10

    anDehazeFormer combines a physics-guided KV cache with per-block adaptive normalization for ultra-high-definition dehazing, but its stated real-time speed and 5x training speedup are not supported by the reported data.

  6. Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A deep unfolding network with complex-valued deformable attention and adaptive bandwidth-preserving propagation improves computer-generated hologram quality (36.45 dB PSNR) and extends working distance.

  7. Uncertainty-Aware Spatial Color Correlation for Low-Light Image Enhancement

    cs.CV 2025-08 conditional novelty 5.0 of 10

    U2CLLIE is a lightweight network for brightening dark images using entropy-guided dual-domain denoising and causal correlation modules, with small PSNR/SSIM gains and mixed LPIPS results.

  8. Degradation-Consistent Learning via Bidirectional Diffusion for Low-Light Image Enhancement

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Training a diffusion model on both enhancement and degradation paths, with a shared encoder and a reflection-aware correction module, yields state-of-the-art low-light enhancement on multiple benchmarks.

  9. Low-light Image Enhancement via Multi-scale Attention combined with Fourier Transform

    cs.CV 2026-07 reject novelty 4.0 of 10

    A Fourier-amplitude-guided multi-scale attention network is claimed to outperform prior low-light enhancement methods by wide margins on LOL, SID, SMID, and SDSD benchmarks.

  10. Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement

    cs.CV 2026-07 conditional novelty 4.0 of 10

    TCA-Net improves low-light image enhancement by replacing fixed-quota Top-K attention with an adaptive confidence threshold for intensity-chromaticity fusion in the HVI color space.

  11. CWNet: Causal Wavelet Network for Low-Light Image Enhancement

    cs.CV 2025-07 conditional novelty 4.0 of 10

    CWNet mixes wavelet-based frequency enhancement, Mamba-style high-frequency scanning, and two semantic consistency losses to produce competitive low-light image enhancement with 1.23 million parameters.

  12. ReF-LLE: Personalized Low-Light Enhancement via Reference-Guided Deep Reinforcement Learning

    cs.CV 2025-06 reject novelty 3.0 of 10

    ReF-LLE iteratively scales the Fourier amplitude (equivalently, the whole image) to match a target average brightness, and reports improved scores on low-light benchmarks.

Pith tools