This work introduces See in the Degraded Extremely Dark (SIDED), a new dataset that applies controlled motion degradation to extremely low-light RAW pairs while retaining their original sensor noise and introduces a physics-guided refinement model to strengthen illumination--reflectance consistency, pixel fidelity, and color preservation without incurring additional inference cost.
Abstract
Extremely low-light RAW enhancement aims to recover severely attenuated sensor signals, yet existing methods often focus on illumination and noise while overlooking the motion-induced degradations inherent in practical low-light imaging. We present a framework for robust extremely low-light RAW enhancement under realistic acquisition degradations. First, we introduce See in the Degraded Extremely Dark (SIDED), a new dataset that applies controlled motion degradation to extremely low-light RAW pairs while retaining their original sensor noise. Second, we propose a unified RAW tokenizer equipped with explicit domain-conditioned representation calibration to align extremely low-light and well-exposed RAW data, followed by a MeanFlow that performs enhancement in a single function evaluation. To our knowledge, this is the first work to formulate extremely low-light RAW enhancement under realistic motion-degraded acquisition and address it with MeanFlow. We further introduce a physics-guided refinement model to strengthen illumination--reflectance consistency, pixel fidelity, and color preservation without incurring additional inference cost. Extensive experiments demonstrate that our framework achieves state-of-the-art performance in extremely low-light RAW enhancement, and robustly handles coupled motion and noise degradations.
SPACE introduces a Depth-Adaptive HVI Transformation to decouple luminance and chrominance under depth guidance, effectively suppressing color-space noise and a Depth-Manifold Modulated Attention mechanism constrains feature interactions within a learned depth manifold, ensuring structural coherence during enhancement.
Yue Zhang, Zhi-Liang Wu, Yuxuan Hou et al.· 0 citations
This work proposes a model-driven deep neural network to effectively handle the joint degradation of low light and blur and designs an illumination enhancement module (IEM) and a reflectance refinement module (RRM) to improve brightness, restore fine details, and suppress noise.
Yao Xiao, You-Shen Xia, Zhen-Yu Lu et al.· IEEE Transactions on Neural...· 0 citations
A Relative Illumination Structure Estimation (RISE) framework is proposed that decouples relative illumination structure from absolute exposure and infers it from reliable bright regions, enabling interpretable and robust enhancement.
Tian-Le Du, Peiyuan He, Hainuo Wang et al.· 0 citations
Existing zero-shot low-light image enhancement methods often underutilize image priors, leading to noise amplification and color distortion. To address these issues, we propose a zero-shot framework for low-light image enhancement. The framework first performs illumination-aware self-supervised denoising to generate a cleaner reference image, which is then used to guide diffusion-based enhancement with a pre-trained backbone. Specifically, the denoising module uses pairwise downsampling together with the proposed illumination prior to suppress noise in dark regions. We then guide the reverse sampling of the pre-trained diffusion model with a refinement strategy operating in both the frequency and spatial domains, so that illumination enhancement and local detail refinement can be jointly achieved during sampling. At each step, Fourier-based reconstruction contributes to illumination enhancement while preserving structural information, and illumination-guided spatial adjustment further refines local brightness. Experiments on multiple benchmark datasets show that the proposed method improves illumination while preserving structural details.
Abstract. Low-light object detection remains fundamentally challenging due to the intrinsic misalignment between physical imaging characteristics and detection-oriented feature representations under extreme illumination degradation. This misalignment originates from the inconsistency between sensor-level signal formation and downstream representation learning, leading to unstable feature distributions and degraded detection performance. Existing approaches either rely on enhancement in the sRGB domain or directly learn from RAW data, yet both struggle to effectively bridge this gap. In this paper, we propose IDAM-RAW, a unified RAW-domain framework that bridges physical imaging processes and detection-oriented representation learning through task-driven end-to-end optimization. Specifically, DetISP maps RAW measurements to detection-friendly features without relying on fixed hardware ISP processing. The Residual Illumination Decoupling Module progressively reduces illumination-related variations in feature space and stabilizes optimization, whereas the Adaptive Feature Modulation Module suppresses interference propagation and enhances target-related responses across multiscale features. To support evaluation, we construct CR7-RAW, a real-world low-light bimodal dataset with spatially paired RAW and RGB observations, providing a new benchmark for RAW-based perception tasks. Extensive experiments on LOD, CR7-RAW, and BDD-Night demonstrate that IDAM-RAW achieves consistent performance gains across the evaluated datasets. Averaged over three independent random seeds, IDAM-RAW improves mAP@50 from 40.3 to 72.7 on LOD while maintaining consistent improvements on CR7-RAW and BDD-Night, supporting its effectiveness and cross-dataset robustness.
Min-Jie Dai, Xing-Yu Lai· Journal of Electronic Imagin...· 0 citations
Reconstructing 3D scenes under real-world low-light conditions remains challenging due to severe sensor noise, low signal-to-noise ratios, and degraded photometric consistency, which destabilize geometry estimation and novel view synthesis. Existing approaches often rely on well-lit reference data for reliable Structure-from-Motion (SfM) initialization under degraded inputs or apply per-view enhancement methods that introduce cross-view inconsistencies. To address these limitations, we propose \textbf{NOVA-GS}, a unified noise-aware framework for low-light 3D Gaussian Splatting that subsumes enhancement, denoising, and geometry optimization within a single process. Our method leverages VGGT-based feed-forward estimation to obtain robust camera poses and geometry directly from degraded inputs, eliminating the need for SfM. Building on this initialization, NOVA-GS integrates three coupled components: a structure-aware enhancement module for exposure correction, a self-supervised denoising module with blind-spot masking for pseudo-supervision, and a consistency-driven Gaussian Splatting optimization enforcing cross-view geometric coherence. We further introduce a noise-guided spherical harmonic regularization to suppress view-dependent artifacts in noisy regions. Extensive experiments on diverse real-world low-light datasets demonstrate improved geometric fidelity, color consistency, and robustness without requiring paired supervision or well-lit references. https://shaurya2524.github.io/nova-gs/
A. ShauryaPavan, Vemunuri Divya Madhuri, Yash Pradeep Gawande et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
