Use This Via API or MCP
Topic pages bundle paper counts, viability trends, author concentration, and top questions into one canonical surface your agents can reference before they open Signal Canvas or create a workspace.
Current research in image restoration is increasingly focused on enhancing model efficiency and adaptability for real-world applications. Recent work emphasizes the integration of advanced techniques such as quantization-aware training and proactive degradation management, which aim to improve performance on edge devices while maintaining visual quality. Innovations like Decoder-Free Distillation and Mamba-Style Transformers are addressing the challenges of model complexity and degradation propagation, enabling more robust restoration across diverse scenarios. Additionally, the exploration of pre-trained diffusion models is revealing their inherent capabilities for restoration tasks, suggesting a shift towards leveraging existing architectures for improved generalization. The field is also seeing a push for unified frameworks that combine restoration with quality assessment, streamlining the process and enhancing output fidelity. These developments not only promise to solve pressing commercial challenges in areas like autonomous driving and surveillance but also highlight a trend towards models that can dynamically adapt to varying degradation conditions.
Quantization-Aware Training (QAT), combined with Knowledge Distillation (KD), holds immense promise for compressing models for edge deployment. However, joint optimization for precision-sensitive imag...
While Transformer-based architectures have dominated recent advances in all-in-one image restoration, they remain fundamentally reactive: propagating degradations rather than proactively suppressing t...
Single image reflection removal (SIRR) is challenging in real scenes, where reflection strength varies spatially and reflection patterns are tightly entangled with transmission structures. This paper ...
Although diffusion-based real-world image restoration (Real-IR) has achieved remarkable progress, efficiently leveraging ultra-large-scale pre-trained text-to-image (T2I) models and fully exploiting t...
Burst image restoration aims to reconstruct a high-quality image from burst images, which are typically captured using manually designed exposure settings. Although these exposure settings significant...
Recent advances in image restoration have enabled high-fidelity recovery of faces from degraded inputs using reference-based face restoration models (Ref-FR). However, such methods focus solely on fac...
While deep learning has advanced single-image deraining, existing models suffer from a fundamental limitation: they employ a static inference paradigm that fails to adapt to the complex, coupled degra...
This paper presents a new ambient light normalization framework, DINOLight, that integrates the self-supervised model DINOv2's image understanding capability into the restoration process as a visual p...
Scanning Probe Microscopy or SPM offers nanoscale resolution but is frequently marred by structured artefacts such as line scan dropout, gain induced noise, tip convolution, and phase hops. While most...
We propose RetinexDualV2, a unified, physically grounded dual-branch framework for diverse Ultra-High-Definition (UHD) image restoration. Unlike generic models, our method employs a Task-Specific Phys...