# Reflection Removal through Efficient Adaptation of Diffusion Transformers

arXiv: https://arxiv.org/abs/2512.05000 · HTML: https://mlsanity.com/paper/2512.05000/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 25 of 25)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [Single Image Reflection Separation with Perceptual Losses](https://mlsanity.com/paper/1806.05376/) (2018)
- [Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis](https://mlsanity.com/paper/2505.09358/) (2025)
- [Single Image Reflection Removal through Cascaded Refinement](https://mlsanity.com/paper/1911.06634/) (2019)
- [Learning to See Through Obstructions](https://mlsanity.com/paper/2004.01180/) (2020)
- [Single Image Reflection Separation via Component Synergy](https://mlsanity.com/paper/2308.10027/) (2023)
- [Revisiting Single Image Reflection Removal In the Wild](https://mlsanity.com/paper/2311.17320/) (2023)
- [Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation](https://mlsanity.com/paper/2110.10546/) (2021)
- [Reversible Decoupling Network for Single Image Reflection Removal](https://mlsanity.com/paper/2410.08063/) (2024)
- [Language-guided Image Reflection Separation](https://mlsanity.com/paper/2402.11874/) (2024)
- [Learned Dual-View Reflection Removal](https://mlsanity.com/paper/2010.00702/) (2020)
- [PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection Removal](https://mlsanity.com/paper/2402.02374/) (2024)
- [Dereflection Any Image with Diffusion Priors and Diversified Data](https://mlsanity.com/paper/2503.17347/) (2025)
- [Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation](https://mlsanity.com/paper/2501.00637/) (2024)
- [OpenRR-1k: A Scalable Dataset for Real-World Reflection Removal](https://mlsanity.com/paper/2506.08299/) (2025)
- [F2T2-HiT: A U-Shaped FFT Transformer and Hierarchical Transformer for Reflection Removal](https://mlsanity.com/paper/2506.05489/) (2025)
- [Single Image Reflection Separation via Dual Prior Interaction Transformer](https://mlsanity.com/paper/2505.12641/) (2025)

## Built on by (most cited first, 4 of 4)

- [NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods](https://mlsanity.com/paper/2604.10321/) (2026)
- [LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models](https://mlsanity.com/paper/2606.02535/) (2026)
- [Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation](https://mlsanity.com/paper/2609.08084/) (2026)
- [From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection](https://mlsanity.com/paper/2608.11562/) (2026)

## Abstract (arXiv)

We introduce a diffusion-transformer (DiT) framework for single-image reflection removal that leverages the generalization strengths of foundation diffusion models in the restoration setting. Rather than relying on task-specific architectures, we repurpose a pre-trained DiT-based foundation model by conditioning it on reflection-contaminated inputs and guiding it toward clean transmission layers. We systematically analyze existing reflection removal data sources for diversity, scalability, and photorealism. To address the shortage of suitable data, we construct a physically based rendering (PBR) pipeline in Blender, built around the Principled BSDF, to synthesize realistic glass materials and reflection effects. Efficient LoRA-based adaptation of the foundation model, combined with the proposed synthetic data, achieves state-of-the-art performance on in-domain and zero-shot benchmarks. These results demonstrate that pretrained diffusion transformers, when paired with physically grounded data synthesis and efficient adaptation, offer a scalable and high-fidelity solution for reflection removal. Project page: https://hf.co/spaces/huawei-bayerlab/windowseat-reflection-removal-web