VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
We present a general strategy to aligning visual generation models -- both image and video generation -- with human preference. To start with, we build VisionReward -- a fine-grained and multi-dimensional reward model. We decompose human preferences in images and videos into multiple dimensions, each represented by a series of judgment questions, linearly weighted and summed to an interpretable and accurate score. To address the challenges of video quality assessment, we systematically analyze various dynamic features of videos, which helps VisionReward surpass VideoScore by 17.2% and achieve top performance for video preference prediction. Based on VisionReward, we develop a multi-objective preference learning algorithm that effectively addresses the issue of confounding factors within preference data. Our approach significantly outperforms existing image and video scoring methods on both machine metrics and human evaluation. All code and datasets are provided at https://github.com/THUDM/VisionReward.
Code (1)
Tasks
Video GenerationVideo Quality AssessmentSimilar Papers 제목 키워드 기반
FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation
Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across multiple dimensions, such as motion nat…
UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs
Existing benchmarks for summarization quality evaluation often lack diverse input scenarios, focus on narrowly defined dimensions (e.g., faithfulness), and struggle with subjective and coarse-grained annotation schemes. …
TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis
While generative text-to-speech (TTS) models approach human-level quality, monolithic metrics fail to diagnose fine-grained acoustic artifacts or explain perceptual collapse. To address this, we propose TTS-PRISM, a mult…
Fine-Grained Human Pose Editing Assessment via Layer-Selective MLLMs
Text-guided human pose editing has gained significant traction in AIGC applications. However,it remains plagued by structural anomalies and generative artifacts. Existing evaluation metrics often isolate authenticity det…
MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models
Multidimensional human understanding is essential for real-world applications such as film analysis and virtual digital humans, yet current LVLM benchmarks largely focus on single-task settings and lack fine-grained, hum…
Reinforcement LearningInstruction Following