RED-Aes learns aesthetic changes from edit-induced image pairs and a new RED-20k dataset via three-stage relative ranking training, claiming SOTA generalization over absolute MOS regression.
hub Canonical reference
Visualquality-r1: Reasoning-inducedimagequalityassessmentviareinforcement learning to rank
Canonical reference. 83% of citing Pith papers cite this work as background.
16
Pith papers citing it
Background
83% of classified citations
hub tools
citation-role summary
background 5
baseline 1
citation-polarity summary
representative citing papers
HiTokSR uses a coarse-to-fine hierarchical tokenizer with frequency-aware sub-codebooks, vision foundation model priors, and index perturbation to achieve state-of-the-art perceptual quality and fidelity in real-world image super-resolution.
PPaint fuses expert pairwise preferences and ratings into ground truth; PSDistill converts VLM pairwise judgments into calibrated pseudo-scores via Elo and trains the same VLM to produce a single-pass aesthetic scorer that improves SRCC across categories.
CaC presents a new spatiotemporal concentrating reward model for video anomalies, built on a novel large-scale dataset and three-stage training with RL and IoU rewards, claiming 25.7% accuracy gains and 11.7% anomaly reduction.
DiNa-LRM introduces a diffusion-native latent reward model using a noise-calibrated Thurstone likelihood on noisy states, matching VLM performance at lower compute in image alignment and preference optimization.
Q-Probe introduces the first agentic IQA framework that scales to high resolutions using context-aware probing, a new Vista-Bench benchmark, and three-stage training to reach state-of-the-art performance across scales.
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
UHD-GCN-BIQA models structural dependencies among sampled patches via a hybrid kNN graph and residual graph convolutions to achieve competitive PLCC and SRCC with the lowest RMSE on the UHD-IQA benchmark for blind ultra-high-definition image quality assessment.
ReasonEdit uses a new CoT dataset and reinforcement learning to produce interpretable, human-aligned evaluations of text-guided image edits.
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
LucidNFT combines a new LR-referenced consistency reward, decoupled normalization, and a real-degradation dataset to improve perceptual quality in flow-matching super-resolution while preserving input fidelity.
DP-DMD preserves sample diversity in few-step image synthesis by applying a teacher-derived target-prediction objective to the first distillation step and standard DMD loss to the rest.
A human preference dataset and VideoReward model enable Flow-DPO and Flow-NRG to produce smoother, better-aligned videos from text prompts in flow-based generators.
OPERA jointly optimizes restoration planning via RL over tool compositions and execution via agent-guided co-training of tools, claiming consistent gains over all-in-one models and prior agent methods on multi-degradation benchmarks.
SmartPhotoCrafter performs automatic photographic image editing by coupling an Image Critic module that identifies deficiencies with a Photographic Artist module that generates edits, trained via multi-stage pretraining, reasoning supervision, and reinforcement learning.
Q-DeepSight proposes a think-with-image multimodal CoT framework trained via RL with perceptual curriculum rewards and evidence gradient filtering to achieve SOTA IQA performance and enable training-free perceptual refinement in image generation.
citing papers explorer
-
Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment
RED-Aes learns aesthetic changes from edit-induced image pairs and a new RED-20k dataset via three-stage relative ranking training, claiming SOTA generalization over absolute MOS regression.
-
HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution
HiTokSR uses a coarse-to-fine hierarchical tokenizer with frequency-aware sub-codebooks, vision foundation model priors, and index perturbation to achieve state-of-the-art perceptual quality and fidelity in real-world image super-resolution.
-
Preferences Order, Ratings Anchor: From Fused Expert Aesthetic Ground Truth to Self-Distillation
PPaint fuses expert pairwise preferences and ratings into ground truth; PSDistill converts VLM pairwise judgments into calibrated pseudo-scores via Elo and trains the same VLM to produce a single-pass aesthetic scorer that improves SRCC across categories.
-
CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
CaC presents a new spatiotemporal concentrating reward model for video anomalies, built on a novel large-scale dataset and three-stage training with RL and IoU rewards, claiming 25.7% accuracy gains and 11.7% anomaly reduction.
-
Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling
DiNa-LRM introduces a diffusion-native latent reward model using a noise-calibrated Thurstone likelihood on noisy states, matching VLM performance at lower compute in image alignment and preference optimization.
-
Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
Q-Probe introduces the first agentic IQA framework that scales to high resolutions using context-aware probing, a new Vista-Bench benchmark, and three-stage training to reach state-of-the-art performance across scales.
-
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
-
Ultra-High-Definition Image Quality Assessment via Graph Representation Learning
UHD-GCN-BIQA models structural dependencies among sampled patches via a hybrid kNN graph and residual graph convolutions to achieve competitive PLCC and SRCC with the lowest RMSE on the UHD-IQA benchmark for blind ultra-high-definition image quality assessment.
-
ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning
ReasonEdit uses a new CoT dataset and reinforcement learning to produce interpretable, human-aligned evaluations of text-guided image edits.
-
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
-
LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
LucidNFT combines a new LR-referenced consistency reward, decoupled normalization, and a real-degradation dataset to improve perceptual quality in flow-matching super-resolution while preserving input fidelity.
-
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
DP-DMD preserves sample diversity in few-step image synthesis by applying a teacher-derived target-prediction objective to the first distillation step and standard DMD loss to the rest.
-
Improving Video Generation with Human Feedback
A human preference dataset and VideoReward model enable Flow-DPO and Flow-NRG to produce smoother, better-aligned videos from text prompts in flow-based generators.
-
OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization
OPERA jointly optimizes restoration planning via RL over tool compositions and execution via agent-guided co-training of tools, claiming consistent gains over all-in-one models and prior agent methods on multi-degradation benchmarks.
-
SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing
SmartPhotoCrafter performs automatic photographic image editing by coupling an Image Critic module that identifies deficiencies with a Photographic Artist module that generates edits, trained via multi-stage pretraining, reasoning supervision, and reinforcement learning.
-
Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement
Q-DeepSight proposes a think-with-image multimodal CoT framework trained via RL with perceptual curriculum rewards and evidence gradient filtering to achieve SOTA IQA performance and enable training-free perceptual refinement in image generation.