Degradations in smart-glasses images obscure small text and fine-grained structures needed by vision-language models (VLMs) for visual assistance. We introduce an high-resolution (HR)-referenced semantic evaluation protocol that compares VLM outputs on restored images with those on corresponding HR references. Our evaluation reveals two failure modes: generative SR can synthesize misleading details, whereas restoration-oriented SR can leave critical evidence blurred or ambiguous. These findings motivate improving faithful detail recovery in restoration-oriented SR, where a key training challenge is to provide sufficiently difficult inputs while retaining recoverable visual information. We propose ReDiC (Recoverability-Difficulty Curriculum), which combines a model-independent recoverability proxy with model-relative restoration difficulty to adapt training degradation severity. ReDiC increases severity when inputs are recoverable and restoration is easy, maintains challenging but recoverable conditions, and reduces severity when estimated recoverability is low. It modifies only training degradation generation, leaving the SR architecture and reconstruction objective unchanged. Across NAFNet, SwinIR, and MambaIR, ReDiC improves average PSNR by approximately 2.5 dB and HR-referenced semantic scores by about 3 points over the corresponding baselines on synthetic benchmarks, with further gains confirmed by LLM-based and human evaluations on 200 real smart-glasses captures.
Figures & tables
Method
Mild PSNR ↑
Medium PSNR ↑
Hard PSNR ↑
Avg. PSNR ↑
Avg. LPIPS ↓
Avg. OCR-NED ↓
Avg. Judge ↑
Avg. Δ Score ↑
LR Input
–
–
–
–
–
0.5490
71.04
–
NAFNet
30.92
29.36
25.44
28.57
0.2825
0.5503
73.54
2.50
NAFNet + ReDiC
33.97
31.41
27.42
30.93
0.2500
0.4860
76.47
5.43
SwinIR
31.02
29.48
25.46
28.65
0.2905
0.5369
73.83
2.79
SwinIR + ReDiC
34.17
31.63
27.34
31.05
0.2361
0.4564
76.87
5.83
MambaIR
31.19
29.54
25.46
28.73
0.2918
0.5390
73.96
2.92
TABLE II : Quantitative comparison of restoration and downstream performance under synthetic degradations. Avg. denotes the mean across three severity levels, and Δ Score denotes the Judge Score gain over LR Input.
Variant
R
D
Sch.
PSNR ↑
OCR-NED ↓
Judge ↑
MambaIR
✗
✗
✗
28.73
0.5390
73.96
Random
✗
✗
✗
26.42
0.5980
70.80
Fixed
✗
✗
✗
27.85
0.5620
72.60
Easy-to-hard
✗
✗
✗
28.95
0.5280
74.18
Shuffled-ReDiC
✓
✓
✗
28.46
0.5480
73.55
D -only
✗
✓
✓
30.24
0.4932
74.85
TABLE IV : Ablation of degradation scheduling and the contributions of recoverability ( R ) and relative difficulty ( D ) on MambaIR. Results are averaged across three severity levels. Sch. denotes the scheduler.
Digital zoom on smartphones relies on learning-based super-resolution (SR) models that operate on RAW sensor images, but obtaining sensor-specific training data is challenging due to the lack of ground-truth images. Synthetic data generation via ``unprocessing'' pipelines offers a potential solution by simulating the degradations that transform high-resolution (HR) images into their low-resolution (LR) counterparts. However, these pipelines can introduce domain gaps due to incomplete or unrealistic degradation modeling. In this paper, we demonstrate that principled and carefully designed degradation modeling can enhance SR performance in real-world conditions. Instead of relying on generic priors for camera blur and noise, we model device-specific degradations through calibration and unprocess publicly available rendered images into the RAW domain of different smartphones. Using these image pairs, we train a single-image RAW-to-RGB SR model and evaluate it on real data from a held-out device. Our experiments show that accurate degradation modeling leads to noticeable improvements, with our SR model outperforming baselines trained on large pools of arbitrarily chosen degradations.
Multimodal large models have shown excellent ability in addressing image super-resolution in real-world scenarios by leveraging language class as condition information, yet their abilities in degraded images remain limited. In this paper, we first revisit the capabilities of the Recognize Anything Model (RAM) for degraded images by calculating text similarity. We find that directly using contrastive learning to fine-tune RAM in the degraded space is difficult to achieve acceptable results. To address this issue, we employ a degradation selection strategy to propose a Real Embedding Extractor (REE), which achieves significant recognition performance gain on degraded image content through contrastive learning. Furthermore, we use a Conditional Feature Modulator (CFM) to incorporate the high-level information of REE for a powerful Mamba-based network, which can leverage effective pixel information to restore image textures and produce visually pleasing results. Extensive experiments demonstrate that the REE can effectively help image super-resolution networks balance fidelity and perceptual quality, highlighting the great potential of Mamba in real-world applications. The source code of this work will be made publicly available at: https://github.com/nathan66666/DACESR.git
Xiaoyan Lei, Wenlong Zhang, Biao Luo +3
School of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, Henan, China. · Shanghai Artificial Intelligence Laboratory, Shanghai 200233, China. · School of Automation, Central South University, Changsha 410083, China. +1
Real-world image super-resolution is particularly challenging for diffusion models because real degradations are complex, heterogeneous, and rarely modeled explicitly. We propose a degradation-aware and structure-preserving diffusion framework for real-world SR. Specifically, we introduce Degradation-aware Token Injection, which encodes lightweight degradation statistics from low-resolution inputs and fuses them with semantic conditioning features, enabling explicit degradation-aware restoration. We further propose Spatially Asymmetric Noise Injection, which modulates diffusion noise with local edge strength to better preserve structural regions during training. Both modules are lightweight add-ons to the adopted diffusion SR framework, requiring only minor modifications to the conditioning pipeline. Experiments on DIV2K and RealSR show that our method delivers competitive no-reference perceptual quality and visually more realistic restoration results than recent baselines, while maintaining a favorable perception--distortion trade-off. Ablations confirm the effectiveness of each module and their complementary gains when combined. The code and model are publicly available at https://github.com/jiyang0315/DASP-SR.git.
Yang Ji, Zonghao Chen, Zhihao Xue +1
KUNBYTE Hangzhou, Zhejiang Province, China · GOLDMYE Xuhui District, Shanghai, China