SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras
RAW images preserve superior fidelity and rich scene information compared to RGB, making them essential for tasks in challenging imaging conditions. To alleviate the high cost of data collection, recent RGB-to-RAW conversion methods aim to synthesize RAW images from RGB. However, they overlook two key challenges: (i) the reconstruction difficulty varies with pixel intensity, and (ii) multi-camera conversion requires camera-specific adaptation. To address these issues, we propose SpiralDiff, a diffusion-based framework tailored for RGB-to-RAW conversion with a signal-dependent noise weighting strategy that adapts reconstruction fidelity across intensity levels. In addition, we introduce CamLoRA, a camera-aware lightweight adaptation module that enables a unified model to adapt to different camera-specific ISP characteristics. Extensive experiments on four benchmark datasets demonstrate the superiority of SpiralDiff in RGB-to-RAW conversion quality and its downstream benefits in RAW-based object detection. Our code and model are available at https://github.com/Chuancy-TJU/SpiralDiff.
Code (0)
등록된 구현이 없습니다.
Tasks
Object DetectionSimilar Papers 제목 키워드 기반
Soft Masked Mamba Diffusion Model for CT to MRI Conversion
Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are the predominant modalities utilized in the field of medical imaging. Although MRI capture the complexity of anatomical structures with greater detail than…
Computed Tomography (CT)Image GenerationMambaMedical Image GenerationEmergence of sector and spiral patterns from a two-species mutualistic cross-feeding model
The ubiquitous existence of microbial communities marks the importance of understanding how species interact within the community to coexist and their spatial organization. We study a two-species mutualistic cross-feedin…
ACE-Net: AutofoCus-Enhanced Convolutional Network for Field Imperfection Estimation with application to high b-value spiral Diffusion MRI
Spatiotemporal magnetic field variations from B0-inhomogeneity and diffusion-encoding-induced eddy-currents can be detrimental to rapid image-encoding schemes such as spiral, EPI and 3D-cones, resulting in undesirable im…
Diffusion MRIImage ReconstructionDreaming of Electrical Waves: Generative Modeling of Cardiac Excitation Waves using Diffusion Models
Electrical waves in the heart form rotating spiral or scroll waves during life-threatening arrhythmias such as atrial or ventricular fibrillation. The wave dynamics are typically modeled using coupled partial differentia…
DenoisingAnnihilation dynamics during spiral defect chaos revealed by particle models
Pair-annihilation events are ubiquitous in a variety of spatially extended systems and are often studied using computationally expensive simulations. Here we develop an approach in which we simulate the pair-annihilation…