Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model

• URL: http://arxiv.org/abs/2601.04033v1
• Date: Wed, 07 Jan 2026 15:47:14 GMT
• Title: Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model
• Authors: Yuan Wang, Borui Liao, Huijuan Huang, Jinda Lu, Ouxiang Li, Kuien Liu, Meng Wang, Xiang Wang,
• Abstract summary: We introduce REACT, a frame-level reward model designed specifically for structural distortions evaluation in generative videos.<n>ReACT assigns point-wise scores and attribution labels by reasoning over video frames, focusing on recognizing distortions.<n>We also present REACT-Bench, a benchmark for generative video distortion evaluation.
• Score: 18.49759441592143
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in video reward models and post-training strategies have improved text-to-video (T2V) generation. While these models typically assess visual quality, motion quality, and text alignment, they often overlook key structural distortions, such as abnormal object appearances and interactions, which can degrade the overall quality of the generative video. To address this gap, we introduce REACT, a frame-level reward model designed specifically for structural distortions evaluation in generative videos. REACT assigns point-wise scores and attribution labels by reasoning over video frames, focusing on recognizing distortions. To support this, we construct a large-scale human preference dataset, annotated based on our proposed taxonomy of structural distortions, and generate additional data using a efficient Chain-of-Thought (CoT) synthesis pipeline. REACT is trained with a two-stage framework: ((1) supervised fine-tuning with masked loss for domain knowledge injection, followed by (2) reinforcement learning with Group Relative Policy Optimization (GRPO) and pairwise rewards to enhance reasoning capability and align output scores with human preferences. During inference, a dynamic sampling mechanism is introduced to focus on frames most likely to exhibit distortion. We also present REACT-Bench, a benchmark for generative video distortion evaluation. Experimental results demonstrate that REACT complements existing reward models in assessing structutal distortion, achieving both accurate quantitative evaluations and interpretable attribution analysis.

Related papers

• Unified Personalized Reward Model for Vision Generation [27.496220369122494]
  We propose UnifiedReward-Flex, a unified personalized reward model for vision generation.<n>We first distill structured, high-quality reasoning traces from advanced closed-source VLMs to bootstrap SFT.<n>We then perform direct preference optimization (DPO) on carefully curated preference pairs to further strengthen reasoning fidelity and discriminative alignment.
  arXiv  Detail & Related papers  (2026-02-02T17:44:21Z)
• VIPER: Process-aware Evaluation for Generative Video Reasoning [64.86465792516658]
  We introduce VIPER, a comprehensive benchmark spanning 16 tasks across temporal, structural, symbolic, spatial, physics, and planning reasoning.<n>Our experiments reveal that state-of-the-art video models achieve only about 20% POC@1.0 and exhibit a significant outcome-hacking.
  arXiv  Detail & Related papers  (2025-12-31T16:31:59Z)
• Content Adaptive based Motion Alignment Framework for Learned Video Compression [72.13599533975413]
  This paper proposes a content adaptive based motion alignment framework.<n>We first introduce a two-stage flow-guided deformable warping mechanism that refines motion compensation with coarse-to-fine offset prediction and mask modulation.<n>Second, we propose a multi-reference quality aware strategy that adjusts distortion weights based on reference quality, and applies it to hierarchical training to reduce error propagation.<n>Third, we integrate a training-free module that downsamples frames by motion magnitude and resolution to obtain smooth motion estimation.
  arXiv  Detail & Related papers  (2025-12-15T02:51:47Z)
• Q-Save: Towards Scoring and Attribution for Generated Video Evaluation [65.83319736145869]
  We present Q-Save, a new benchmark dataset and model for holistic evaluation of AI-generated video (AIGV) quality.<n>The dataset contains near 10000 videos, each annotated with a scalar mean opinion score (MOS) and fine-grained attribution labels.<n>We propose a unified evaluation model that jointly performs quality scoring and attribution-based explanation.
  arXiv  Detail & Related papers  (2025-11-24T07:00:21Z)
• FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning [65.42201665046505]
  Current video understanding models rely on fixed frame sampling strategies, processing predetermined visual inputs regardless of the specific reasoning requirements of each question.<n>This static approach limits their ability to adaptively gather visual evidence, leading to suboptimal performance on tasks that require broad temporal coverage or fine-grained spatial detail.<n>We introduce FrameMind, an end-to-end framework trained with reinforcement learning that enables models to dynamically request visual information during reasoning through Frame-Interleaved Chain-of-Thought (FiCOT)<n>Unlike traditional approaches, FrameMind operates in multiple turns where the model alternates between textual reasoning and active visual perception, using tools to extract
  arXiv  Detail & Related papers  (2025-09-28T17:59:43Z)
• Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements [83.5820690348833]
  We present a framework for low-level vision tasks that does not require any external training data corpus. Our approach learns neural modules by optimizing over a corrupted sequence, leveraging the weights of the coherence-temporal test and statistics internal statistics.
  arXiv  Detail & Related papers  (2023-12-13T01:57:11Z)
• Corner-to-Center Long-range Context Model for Efficient Learned Image Compression [70.0411436929495]
  In the framework of learned image compression, the context model plays a pivotal role in capturing the dependencies among latent representations. We propose the textbfCorner-to-Center transformer-based Context Model (C$3$M) designed to enhance context and latent predictions. In addition, to enlarge the receptive field in the analysis and synthesis transformation, we use the Long-range Crossing Attention Module (LCAM) in the encoder/decoder.
  arXiv  Detail & Related papers  (2023-11-29T21:40:28Z)
• Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness [4.339574774938128]
  We present a novel framework for generating adversarial benchmarks to evaluate the robustness of image classification models. Our framework allows users to customize the types of distortions to be optimally applied to images, which helps address the specific distortions relevant to their deployment.
  arXiv  Detail & Related papers  (2023-10-28T07:40:42Z)
• Diffusion Probabilistic Modeling for Video Generation [17.48026395867434]
  Denoising diffusion probabilistic models are a promising new class of generative models that are competitive with GANs on perceptual metrics. Inspired by recent advances in neural video compression, we use denoising diffusion models to generate a residual baseline to a deterministic next-frame prediction. We find significant improvements in terms of perceptual quality on all data and improvements in terms of frame forecasting for complex high-resolution videos.
  arXiv  Detail & Related papers  (2022-03-16T03:52:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.