Pith. sign in

REVIEW 4 cited by

Self-Reference Deep Adaptive Curve Estimation for 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 2308.08197 v4 pith:SQWQI5AX submitted 2023-08-16 eess.IV cs.CV

Jianyu Wen , Chenhao Wu , Tong Zhang , Yixuan Yu , Piotr Swierczynski This is my paper
classification eess.IVcs.CV
keywords enhancementimageadaptivecurvedeeplow-lightnoisestage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we propose a 2-stage low-light image enhancement method called Self-Reference Deep Adaptive Curve Estimation (Self-DACE). In the first stage, we present an intuitive, lightweight, fast, and unsupervised luminance enhancement algorithm. The algorithm is based on a novel low-light enhancement curve that can be used to locally boost image brightness. We also propose a new loss function with a simplified physical model designed to preserve natural images' color, structure, and fidelity. We use a vanilla CNN to map each pixel through deep Adaptive Adjustment Curves (AAC) while preserving the local image structure. Secondly, we introduce the corresponding denoising scheme to remove the latent noise in the darkness. We approximately model the noise in the dark and deploy a Denoising-Net to estimate and remove the noise after the first stage. Exhaustive qualitative and quantitative analysis shows that our method outperforms existing state-of-the-art algorithms on multiple real-world datasets.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. SIMI: Self-information Mining Network for Low-light Image Enhancement

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    SIMI is an unsupervised low-light image enhancement network using bit-plane decomposition to mine self-information, reported to reach state-of-the-art performance on standard benchmarks.

  2. Reading in the Dark: Low-light Scene Text Recognition

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    Introduces LSTR and ESTR low-light text datasets and shows joint LLIE-OCR training outperforms standalone models.

  3. Towards Lightest Low-Light Image Enhancement Architecture for Mobile Devices

    cs.CV 2025-07 unverdicted novelty 5.0 of 10

    LiteIE proposes a two-layer backbone-agnostic feature extractor and parameter-free Iterative Restoration Module for unsupervised low-light enhancement, claiming 19.04 dB PSNR on LOL with 0.07% of SOTA parameters and 3...

  4. Self-DACE++: Robust Low-Light Enhancement via Efficient Adaptive Curve Estimation

    cs.CV 2026-04 unverdicted novelty 4.0 of 10

    Self-DACE++ enhances low-light images more effectively than prior methods via efficient adaptive adjustment curves, randomized-order training with network fusion, and a Retinex-grounded denoising module while achievin...

Pith tools