Tagged articles
image restoration
29 articles · Page 1 of 1
TTTIR introduces a test-time training framework that models image restoration as progressive instance-specific state evolution, using a Progressive State Sequence Generator for target trajectories and a State Transition Evolver for adaptive operator updates, achieving state-of-the-art results on low-light enhancement, deraining, and dehazing benchmarks with minimal parameters.
Deep LearningDehazingDeraining
0 likes · 9 min read

SmartPhotoCrafter introduces a unified reasoning-to-generation framework for automatic photo enhancement: an Image Critic analyzes quality via chain-of-thought reasoning, then a Photographic Artist performs high-fidelity restoration and aesthetic retouching, unifying dehazing, deblurring, and color grading without explicit user instructions, trained via a three-stage strategy with multi-level rewards.
SmartPhotoCrafterautomatic photo enhancementchain-of-thought
0 likes · 13 min read

Xiaomi's AI team showcased twelve ECCV 2026 papers that advance visual understanding and generation, including a single‑step high‑quality face‑video restoration method, a streaming VideoLLM that thinks while watching with a 15.7× speed boost, relative aesthetic scoring, GUI agents, in‑image translation, multimodal retrieval, and several autonomous‑driving world‑model breakthroughs.
Autonomous DrivingComputer Visionimage restoration
0 likes · 21 min read

LearnIR tackles real‑world image restoration under heterogeneous degradations by training a lightweight network to predict gradient‑correction distributions for diffusion posterior sampling without a forward operator, and adds a dynamic‑resolution module that further suppresses noise, achieving state‑of‑the‑art PSNR, SSIM and LPIPS on multiple benchmarks.
DehazingLearnIRdiffusion models
0 likes · 10 min read

LiveMoments, the first method dedicated to restoring the quality of reselected cover frames in Live Photos, leverages the original high‑resolution cover as a reference and a motion‑alignment module within a diffusion model to correct motion misalignment and achieve high‑definition results, as demonstrated on two real datasets and a synthetic benchmark.
ICLR 2026Live Photoimage restoration
0 likes · 9 min read

Xiaomi secured three top spots at CVPR 2026 NTIRE—first in Efficient Super‑Resolution with SPANV2, first in Portrait Restoration using a dual‑stage cascade, and second in Reflection Removal via RDNet‑XL and diffusion‑model distillation—showcasing hardware‑software co‑design, ultra‑fast inference, and novel algorithmic innovations.
diffusion model distillationefficient inferencehardware-software co-design
0 likes · 14 min read

The paper "LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference‑guided Diffusion" introduces a new task and a diffusion‑based method that uses the original high‑resolution cover frame to dramatically improve the visual quality of reselection cover frames in Live Photos, outperforming existing reference‑super‑resolution and single‑frame approaches.
ICLR 2026Live PhotoMobile Imaging
0 likes · 8 min read


AIWalkerApr 10, 2026 · Artificial Intelligence
RealRestorer leverages large‑scale image‑editing models, a hybrid synthetic‑and‑real degradation pipeline, and a two‑stage training strategy to deliver state‑of‑the‑art open‑source restoration that generalizes across nine real‑world degradation types while preserving content consistency.
Computer VisionDeep LearningReal-World Data
0 likes · 13 min read


AIWalkerApr 6, 2026 · Artificial Intelligence
The TPAMI 2025 paper introduces BIPNet, a unified burst‑image framework that tackles alignment, fusion, and upsampling challenges with edge‑enhanced alignment, pseudo‑burst feature fusion, and adaptive group upsampling, achieving state‑of‑the‑art results across super‑resolution, low‑light enhancement, and denoising while offering lightweight mobile variants.
BIPNetBurst Image ProcessingComputer Vision
0 likes · 13 min read


AIWalkerApr 6, 2026 · Artificial Intelligence
The paper introduces TIR‑Agent, an image‑restoration agent that learns a tool‑calling policy via supervised fine‑tuning and reinforcement learning, addressing exploration stagnation and multi‑objective reward imbalance, and demonstrates over 2.5× faster inference and superior multi‑metric performance on synthetic and real degradation datasets.
Computer VisionMulti-Objective OptimizationTool Scheduling
0 likes · 18 min read

This article presents Ada-RefSR, a novel single‑step diffusion‑based reference super‑resolution framework that introduces a "Trust but Verify" paradigm, adaptive implicit correlation gating, and lightweight architecture to robustly suppress hallucinations and achieve state‑of‑the‑art performance on multiple benchmarks, while being suitable for mobile deployment.
Ada-RefSRICLR2026diffusion
0 likes · 10 min read

This article evaluates the Nano Banana Pro text‑to‑image model, built on Gemini 3 Pro, across fourteen low‑level vision tasks and forty datasets using only prompts without fine‑tuning, revealing strong perceptual quality but weak pixel‑level metrics, and highlighting both its generative strengths and failure modes such as hallucinations and color shifts.
AI model analysisZero-shot Evaluationimage restoration
0 likes · 7 min read

This article examines the cutting‑edge AI techniques—multimodal fusion, deep‑learning disease detection, reversible repair, diffusion‑Transformer models, GAN‑based pattern generation, and AR navigation—that enable millimetre‑level digital restoration and cultural democratization of the Dunhuang murals.
AIARCultural Heritage
0 likes · 14 min read


Amap TechJul 9, 2025 · Artificial Intelligence
This article introduces VMBench, the first perception‑aligned video motion generation benchmark that defines a five‑dimensional metric suite and a meta‑guided prompt generation pipeline, and presents LD‑RPS, a zero‑shot unified image restoration framework based on latent diffusion recurrent posterior sampling, together with extensive experiments validating both systems.
benchmarkdiffusion modelsimage restoration
0 likes · 14 min read


Amap TechJul 9, 2025 · Artificial Intelligence
This article introduces VMBench, a perception‑aligned video motion generation benchmark with a five‑dimensional metric suite and meta‑guided prompt generation, and LD‑RPS, a zero‑shot unified image restoration framework using latent diffusion and recurrent posterior sampling, detailing their motivations, innovations, experiments, and future directions.
AI researchdiffusion modelsimage restoration
0 likes · 14 min read

The article presents MaIR, a locality‑ and continuity‑preserving Mamba‑based model for image restoration, detailing its three‑stage architecture, novel scanning strategy, loss functions, experimental results on super‑resolution and denoising, and ablation studies, with links to the arXiv paper and source code.
Computer VisionDenoisingMamba
0 likes · 5 min read

The article presents MaIR, a Mamba‑based image restoration model that preserves locality and continuity, detailing its architecture, scanning strategies, loss functions, experimental results on super‑resolution and denoising, and an ablation study, while providing links to the arXiv paper and GitHub source code.
Computer VisionDenoisingMamba
0 likes · 5 min read

The paper introduces HINT, a Transformer‑based image restoration model that employs Hierarchical Multi‑Head Attention (HMHA) and a Query‑Key Cache Updating (QKCU) module to eliminate attention redundancy, achieving superior PSNR/SSIM scores across low‑light enhancement, dehazing, desnowing, denoising, and deraining tasks while maintaining low model complexity.
Computer VisionHierarchical AttentionTransformer
0 likes · 10 min read


AIWalkerApr 8, 2025 · Artificial Intelligence
AgenticIR combines visual language models and large language models in a multi‑stage reasoning workflow—perception, planning, execution, reflection, and adjustment—to evaluate, plan, and iteratively apply specialized restoration tools, achieving superior results on complexly degraded images compared to baseline methods.
Agentic SystemsICLR 2025Vision-Language Models
0 likes · 15 min read

Introducing MambaIRv2, an image restoration backbone that replaces Mamba’s causal scanning with an attentive state‑space module, achieving single‑direction scanning, reduced parameters and computation, and superior performance on lightweight and classic super‑resolution, JPEG artifact removal, and denoising tasks, as validated by CVPR‑2025 results.
AttentionComputer VisionMambaIRv2
0 likes · 8 min read


AIWalkerMar 3, 2025 · Artificial Intelligence
This paper introduces a lightweight Diffusion Restoration Adapter that integrates into pre‑trained diffusion priors such as StableDiffusion XL and StableDiffusion 3, dramatically reduces parameter overhead compared with ControNet, and delivers superior quantitative and visual results on real‑world image restoration benchmarks through a novel sampling strategy.
AIAdapterStableDiffusion
0 likes · 17 min read


AIWalkerFeb 6, 2025 · Artificial Intelligence
FluxSR introduces a novel single‑step diffusion approach for real‑world image super‑resolution built on the 12‑billion‑parameter FLUX.1‑dev model, employing Flow‑Trajectory Distillation, TV‑LPIPS and attention‑diversity losses to achieve high fidelity, reduced artifacts, and lower memory and compute costs.
Flow Distillationdiffusionimage restoration
0 likes · 16 min read

Kuaishou has achieved a significant milestone with 7 papers accepted at AAAI 2025, covering diverse AI research areas including video processing, recommendation systems, and image restoration, demonstrating the company's strong research capabilities in artificial intelligence.
AAAI 2025KuaishouMachine Learning
0 likes · 10 min read

This article explains how diffusion equation methods can be applied to digitally repair spotted paintings, covering the mathematical representation of images, the underlying heat‑transfer analogy, step‑by‑step inpainting procedures, and improvements such as total variation flow to preserve edges.
Computer Visiondiffusion equationimage restoration
0 likes · 4 min read

Xiaohongshu’s audio‑video architecture team secured second place in the RAIM challenge and first in the S‑UGC VQA challenge at CVPR NTIRE 2024 by improving generative image restoration with SUPIR, DeSRA and a Fusion model, and enhancing video quality assessment using LIQE, Q‑Align and FAST‑VQA, then deploying these methods for live‑stream denoising, intelligent transcoding and cloud‑based super‑resolution, achieving high PLCC/SROCC scores and up to 33 % bandwidth savings.
AICVPR NTIRE 2024Deep Learning
0 likes · 25 min read

Alibaba Cloud’s PAI platform showcased three breakthrough papers at ICCV 2023—including the Scale‑Aware Modulation Transformer for efficient vision backbones, the Stable‑DINO detection transformer with improved matching, and a non‑invasive fingerprinting method for deep image‑restoration models—highlighting its growing impact in AI research.
Model FingerprintingTransformerimage restoration
0 likes · 10 min read

Real‑CUGAN is an open‑source AI super‑resolution model that upscales anime video up to 4× using a million‑patch, frequency‑domain‑supervised dataset, delivering faster inference than Real‑ESRGAN, seamless Waifu2x compatibility, and superior texture, line and artifact handling, with code released on GitHub.
AI super-resolutionDeep LearningReal-CUGAN
0 likes · 8 min read

Image clarity impacts daily life, from personal memories to security, and Kuaishou’s Y‑Tech team tackles degradation by constructing paired low‑high quality datasets and a style‑based AI model that leverages facial masks to restore high‑definition portraits, preserving identity while enhancing detail.
AIComputer VisionDeep Learning
0 likes · 10 min read

The article presents a mobile‑first solution that converts a single RGB photograph into an interactive 3D photo by combining learning‑based monocular depth estimation, multi‑task image‑and‑depth restoration, face‑specific refinement, and a custom KwaiNN inference engine to achieve real‑time rendering on all smartphone models without requiring depth sensors.
3D PhotoARKwaiNN
0 likes · 16 min read
