English(EN) Self-DACE++: Robust Low-Light Enhancement via Efficient Adaptive Curve Estimation

Self-DACE++ 通过轻量级、高效的自适应曲线改进低光图像增强

作者 PulseAugur 编辑部 · [3 个来源] · 2026-04-28 08:33

研究人员开发了 Self-DACE++，一个用于增强低光图像的先进框架。该新系统通过引入增强的自适应调整曲线 (AAC) 来改进其前身 Self-DACE，在保持图像质量的同时具有计算效率。该框架还包含一个基于物理的客观函数和一个用于有效处理噪声的去噪模块。 AI

影响为低光条件下的实时图像增强提供了改进的能力，可能使摄影和计算机视觉领域的应用受益。

排序理由这是一篇描述低光图像增强新方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 3 个来源。我们如何撰写摘要 →

报道来源 [3]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-04-28 08:33

Self-DACE++：通过高效自适应曲线估计实现鲁棒的低光照增强

In this paper, we present Self-DACE++, an improved unsupervised and lightweight framework for Low-Light Image Enhancement (LLIE), building upon our previous Self-Reference Deep Adaptive Curve Estimation (Self-DACE). To better address the trade-off between computational efficiency…
arXiv cs.CV TIER_1 English(EN) · Jianyu Wen, Jun Xie, Feng Chen, Zhepeng Wang, Chenhao Wu, Tong Zhang, Yixuan Yu, Piotr Swierczynski · 2026-04-29 04:00

Self-DACE++：通过高效自适应曲线估计实现鲁棒的低光照增强

arXiv:2604.25367v1 Announce Type: new Abstract: In this paper, we present Self-DACE++, an improved unsupervised and lightweight framework for Low-Light Image Enhancement (LLIE), building upon our previous Self-Reference Deep Adaptive Curve Estimation (Self-DACE). To better addres…
arXiv cs.CV TIER_1 English(EN) · Piotr Swierczynski · 2026-04-28 08:33

Self-DACE++：通过高效自适应曲线估计实现鲁棒的低光照增强

In this paper, we present Self-DACE++, an improved unsupervised and lightweight framework for Low-Light Image Enhancement (LLIE), building upon our previous Self-Reference Deep Adaptive Curve Estimation (Self-DACE). To better address the trade-off between computational efficiency…