# ODDR: One-Step Deshadow Diffusion via Reward Guidance

arXiv: https://arxiv.org/abs/2610.01291 · HTML: https://mlsanity.com/paper/2610.01291/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 49 of its 69 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 30 of 49)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [One-Step Effective Diffusion Network for Real-World Image Super-Resolution](https://mlsanity.com/paper/2406.08177/) (2024)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [Rich Human Feedback for Text-to-Image Generation](https://mlsanity.com/paper/2312.10240/) (2023)
- [Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN](https://mlsanity.com/paper/1911.08718/) (2019)
- [ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2212.04711/) (2022)
- [Shadow Removal via Shadow Image Decomposition](https://mlsanity.com/paper/1908.08628/) (2019)
- [Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach](https://mlsanity.com/paper/2412.03017/) (2024)
- [Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data](https://mlsanity.com/paper/1903.10683/) (2019)
- [T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback](https://mlsanity.com/paper/2405.18750/) (2024)
- [Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think](https://mlsanity.com/paper/2409.11355/) (2024)

## Abstract (arXiv)

Recent advances in deep learning for shadow removal have significantly enhanced image quality and realism. However, most approaches rely on real-world paired datasets, which are costly to collect and often limited in scene diversity, leading to limited generalization. To address these limitations, we propose One-step Deshadow Diffusion via Reward guidance (ODDR), a new framework that achieves efficient and high-fidelity shadow removal without relying on real-world paired supervision. Our method begins with One-step Deshadow Diffusion (ODD), a baseline model trained on synthetic shadow data for efficient one-step shadow-free reconstruction. We further adapt ODD into ODDR using ShadowReward. In contrast to traditional, annotation-heavy approaches, ShadowReward is the first reward model for shadow removal trained entirely without human annotation. It learns to mimic human perceptual judgments by ranking synthetically generated images with controlled degradations, such as texture distortion and boundary artifacts. This reward-guided fine-tuning enables ODDR to close the synthetic-to-real domain gap. Extensive experiments show that ODD achieves strong performance without relying on real-world paired supervision, and ODDR further improves the results, narrowing the gap to fully supervised methods trained on real-world paired data while maintaining higher computational efficiency as a single-step model.