Search papers, labs, and topics across Lattice.
Self-DACE++ is introduced as an improved unsupervised framework for low-light image enhancement, building on Self-DACE. It uses enhanced Adaptive Adjustment Curves (AACs) with minimal trainable parameters to adjust dynamic range while preserving image quality. The framework employs a randomized order training strategy and network fusion for an efficient iterative inference structure, alongside a physics-grounded objective function and denoising module.
Achieve state-of-the-art low-light image enhancement with real-time inference using an extremely lightweight and unsupervised framework.
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 and restoration quality, Self-DACE++ introduces enhanced Adaptive Adjustment Curves (AACs). These curves, governed by minimal trainable parameters, flexibly adjust the dynamic range while preserving the color fidelity, structural integrity, and naturalness of the enhanced images. To achieve an extremely lightweight architecture without sacrificing performance, we propose a randomized order training strategy coupled with a network fusion mechanism, which compresses the model into an efficient iterative inference structure. Furthermore, we formulate a physics-grounded objective function based on Retinex theory and incorporate a dedicated denoising module to effectively estimate and suppress latent noise in dark regions. Extensive qualitative and quantitative evaluations on multiple real-world benchmark datasets demonstrate that Self-DACE++ outperforms existing state-of-the-art methods, delivering superior enhancement quality with real-time inference capability. The code is available at https://github.com/John-Wendell/Self-DACE.
