# SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras

arXiv: https://arxiv.org/abs/2603.14885 · HTML: https://mlsanity.com/paper/2603.14885/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 51 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 30 of 41)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting](https://mlsanity.com/paper/2307.12348/) (2023)
- [SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution](https://mlsanity.com/paper/2311.16518/) (2023)
- [DiffIR: Efficient Diffusion Model for Image Restoration](https://mlsanity.com/paper/2303.09472/) (2023)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [Implicit Style-Content Separation using B-LoRA](https://mlsanity.com/paper/2403.14572/) (2024)
- [Low-Light Image Enhancement with Wavelet-based Diffusion Models](https://mlsanity.com/paper/2306.00306/) (2023)
- [Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model](https://mlsanity.com/paper/2308.13164/) (2023)
- [Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach](https://mlsanity.com/paper/2412.03017/) (2024)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Global Structure-Aware Diffusion Process for Low-Light Image Enhancement](https://mlsanity.com/paper/2310.17577/) (2023)
- [Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes](https://mlsanity.com/paper/2003.14013/) (2020)
- [Efficient Diffusion Model for Image Restoration by Residual Shifting](https://mlsanity.com/paper/2403.07319/) (2024)
- [K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs](https://mlsanity.com/paper/2502.18461/) (2025)
- [Model-Based Image Signal Processors via Learnable Dictionaries](https://mlsanity.com/paper/2201.03210/) (2022)
- [Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model](https://mlsanity.com/paper/2503.18512/) (2025)
- [GenISP: Neural ISP for Low-Light Machine Cognition](https://mlsanity.com/paper/2205.03688/) (2022)
- [Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata](https://mlsanity.com/paper/2206.01813/) (2022)
- [UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion](https://mlsanity.com/paper/2501.11515/) (2025)

## Abstract (arXiv)

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.