# X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge

arXiv: https://arxiv.org/abs/2605.13258 · HTML: https://mlsanity.com/paper/2605.13258/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 5 of 5)

- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration](https://mlsanity.com/paper/2412.01427/) (2024)
- [WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restoration](https://mlsanity.com/paper/2509.11642/) (2025)
- [Restormer-Plus for Real World Image Deraining: One State-of-the-Art Solution to the GT-RAIN Challenge (CVPR 2023 UG2+ Track 3)](https://mlsanity.com/paper/2305.05454/) (2023)

## Built on by (most cited first, 2 of 2)

- [The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results](https://mlsanity.com/paper/2607.21118/) (2026)
- [The Domain Is a Residue: Adapting Self-Supervised Features, Not Generators](https://mlsanity.com/paper/2609.37330/) (2026)

## Abstract (arXiv)

In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions. Our method is built upon the X-Restormer baseline, which captures both channel-wise global dependencies and spatially-local structural information through its dual-attention design (Multi-DConv Head Transposed Attention and Overlapping Cross-Attention), augmented with the spatially-adaptive input scaling mechanism from Restormer-Plus. We adopt a two-stage training strategy with dual-model ensemble inference. In the first stage, Model B is trained from scratch on a large-scale diverse dataset randomly sampled from the FoundIR training set (approximately 800 GB out of 4.84 TB), covering five degradation types: blur, haze, rain, snow, and composite conditions such as co-occurring rain and haze. In the second stage, Model A is fine-tuned on the WeatherStream dataset (rain and snow splits) using Model B's final checkpoint as pretrained initialization, enabling efficient domain adaptation with a substantially smaller dataset. To better preserve structural details during training, we propose a novel Gradient-Guided Edge-Aware (GGEA) Loss, which applies Sobel operators to the ground-truth image to construct a spatially adaptive weight map that assigns higher supervision to edge and high-frequency regions. This is incorporated alongside L1 and Multi-Scale SSIM losses in a unified training objective. At inference time, predictions from the two models are fused via a weighted average, out = 0.4 x outA + 0.6 x outB, where the higher weight assigned to Model B reflects its stronger generalization ability from large-scale pretraining. With these strategies, our proposed method successfully ranks 1st in the challenge.