# RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration

arXiv: https://arxiv.org/abs/2509.12039 · HTML: https://mlsanity.com/paper/2509.12039/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 81 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Builds on (most cited first, 30 of 57)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Deep Joint Rain Detection and Removal from a Single Image](https://mlsanity.com/paper/1609.07769/) (2016)
- [Images Speak in Images: A Generalist Painter for In-Context Visual Learning](https://mlsanity.com/paper/2212.02499/) (2022)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Density-aware Single Image De-raining using a Multi-stream Dense Network](https://mlsanity.com/paper/1802.07412/) (2018)
- [Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining](https://mlsanity.com/paper/1807.05698/) (2018)
- [Image De-raining Using a Conditional Generative Adversarial Network](https://mlsanity.com/paper/1701.05957/) (2017)
- [InstructIR: High-Quality Image Restoration Following Human Instructions](https://mlsanity.com/paper/2401.16468/) (2024)
- [Clearing the Skies: A deep network architecture for single-image rain removal](https://mlsanity.com/paper/1609.02087/) (2016)
- [Interpreting Super-Resolution Networks with Local Attribution Maps](https://mlsanity.com/paper/2011.11036/) (2020)
- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [Controlling Vision-Language Models for Multi-Task Image Restoration](https://mlsanity.com/paper/2310.01018/) (2023)
- [OneRestore: A Universal Restoration Framework for Composite Degradation](https://mlsanity.com/paper/2407.04621/) (2024)
- [Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement](https://mlsanity.com/paper/2302.11831/) (2023)

## Built on by (most cited first, 1 of 1)

- [Collapse of Patches: Ranking Image Patches for Efficient Visual Modeling](https://mlsanity.com/paper/2511.22281/) (2025)

## Abstract (arXiv)

This work presents Robust Representation Learning via Adaptive Mask (RAM++), a two-stage framework for all-in-one image restoration. RAM++ integrates high-level semantic understanding with low-level texture generation to achieve content-oriented robust restoration. It addresses the limitations of existing degradation-oriented methods in extreme scenarios (e.g., degradations strongly coupled with image structures). RAM++ also mitigates common challenges such as unbalanced performance across tasks, overfitting to seen degradations, and weak generalization to unseen ones through three key designs: 1) Adaptive Semantic-Aware Mask (AdaSAM): a pretraining strategy that applies pixel-level masks to semantically rich and textured regions. This design enables the network to learn both generative priors and image content priors from various degradations. 2) Mask Attribute Conductance (MAC): a selective fine-tuning strategy that adjusts the layers with higher contributions to bridge the integrity gap between masked pretraining and full-image fine-tuning while retaining learned priors. 3) Robust Feature Regularization (RFR): a strategy that leverages DINOv2's semantically consistent and degradation-invariant representations, together with efficient feature fusion, to achieve faithful and semantically coherent restoration. With these designs, RAM++ achieves robust, well-balanced, and state-of-the-art performance across seen, unseen, extreme, and mixed degradations. Our code and model will be released at https://github.com/DragonisCV/RAM