EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

• URL: http://arxiv.org/abs/2605.23271v1
• Date: Fri, 22 May 2026 06:22:21 GMT
• Title: EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation
• Abstract summary: We introduce EvalVerse, a comprehensive, pipeline-aware, and expert-calibrated evaluation framework.<n>First, we organize domain knowledge into an evaluation taxonomy aligned with the professional filmmaking workflow.<n>Second, we distill human expert judgments into a curated dataset with large-scale human annotations.<n>Third, we inject this knowledge into Vision-Language Models (VLMs) through an expert-calibrated fine-tuning strategy.
• Score: 59.569634087474185
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The rapid evolution of generative video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community transitions towards Reinforcement Learning (RL) and agentic workflows. However, reliable evaluation has emerged as a critical bottleneck. Existing benchmarks predominantly evaluate ''whether it is right'' (basic prompt-following) while fundamentally neglecting ''whether it is good'' (cinematic quality, acting, and aesthetics). Furthermore, current automated metrics lack the domain-specific rigor required to provide trustworthy signals, creating a severe credibility gap between human aesthetic perception and machine scoring. To bridge this gap, we introduce EvalVerse, a comprehensive, pipeline-aware, and expert-calibrated evaluation framework. We treat video generation assessment not merely as an engineering task, but as a core scientific problem: the systematic digitization of subjective cinematic expertise. First, we organize domain knowledge into an evaluation taxonomy aligned with the professional filmmaking workflow (pre-production, production, and post-production). Second, we distill human expert judgments into a curated dataset with large-scale human annotations. Third, we inject this knowledge into Vision-Language Models (VLMs) through an expert-calibrated fine-tuning strategy, enabling the VLM to perform explicit Chain-of-Thought reasoning. Compared to previous works, EvalVerse not only retains compatibility with foundational ''rightness'' metrics, but also significantly expands the criteria to ''goodness'' and broaden the task coverage to complex multi-shot sequencing and audio-visual integration. Consequently, by providing granular diagnostic signals, EvalVerse transcends a static leaderboard and establishes a fundamental infrastructure for future work, such as reward models and evaluator agent.

Related papers

• AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models [37.78996308837551]
  We introduce AVBench, a fully automated benchmark tailored for human-centric AV generation.<n> AVBench integrates ten evaluation dimensions designed for human-centered real-world scenarios.<n>It derives continuous evaluation scores from the model's prediction confidence on binary decisions.
  arXiv  Detail & Related papers  (2026-05-23T16:42:39Z)
• Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement [58.15004031934379]
  We propose Q-DeepSight, a think-with-image framework that emulates this human-like process.<n>Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content.<n>We demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement.
  arXiv  Detail & Related papers  (2026-04-18T06:10:57Z)
• Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models [15.709482146201283]
  A simple linear classifier trained on the frozen features of modern Vision Foundation Models establishes a new state-of-the-art.<n>We show that this baseline matches specialized detectors on standard benchmarks but also decisively outperforms them on in-the-wild datasets.<n>We conclude by advocating for a paradigm shift in AI forensics, moving from overfitting on static benchmarks to harnessing the evolving world knowledge of foundation models for real-world reliability.
  arXiv  Detail & Related papers  (2026-02-02T07:20:02Z)
• Trustworthy Evaluation of Robotic Manipulation: A New Benchmark and AutoEval Methods [30.612032540735402]
  We propose a solution that combines the Eval-Actions benchmark and the AutoEval architecture.<n>This dataset is structured around three core supervision signals: Expert Grading (EG), Rank-Guided preferences (RG), and Chain-of-Thought (CoT)<n>Experiments show AutoEval achieves Spearman's Rank Correlation Coefficients (SRCC) of 0.81 and 0.84 under the EG and RG protocols, respectively.
  arXiv  Detail & Related papers  (2026-01-26T17:47:42Z)
• 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)
• NovisVQ: A Streaming Convolutional Neural Network for No-Reference Opinion-Unaware Frame Quality Assessment [39.76658525158528]
  Video quality assessment (VQA) is vital for computer vision tasks, but existing approaches face major limitations.<n>We present a scalable, streaming-based VQA model that is both no-reference and opinion-unaware.
  arXiv  Detail & Related papers  (2025-11-06T18:23:55Z)
• Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation [78.24409139109507]
  We introduce Stable Cinemetrics, a framework that formalizes filmmaking controls into four disentangled, hierarchical control nodes.<n>We conduct a large-scale human study spanning 10+ models and 20K videos, annotated by a pool of 80+ film professionals.<n>SCINE is the first approach to situate professional video generation within the landscape of video generative models.
  arXiv  Detail & Related papers  (2025-09-30T17:22:18Z)
• EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation [17.37840331449749]
  We propose a self-Evolving Pairwise Reasoning (EvolvR) framework for story evaluation.<n>The framework first self-synthesizes score-aligned Chain-of-Thought (CoT) data via a multi-persona strategy.<n>The evaluator trained on the refined data is deployed as a reward model to guide the story generation task.
  arXiv  Detail & Related papers  (2025-08-08T06:10:47Z)
• VACT: A Video Automatic Causal Testing System and a Benchmark [55.53300306960048]
  VACT is an **automated** framework for modeling, evaluating, and measuring the causal understanding of VGMs in real-world scenarios.<n>We introduce multi-level causal evaluation metrics to provide a detailed analysis of the causal performance of VGMs.
  arXiv  Detail & Related papers  (2025-03-08T10:54:42Z)
• Video Annotator: A framework for efficiently building video classifiers using vision-language models and active learning [0.0]
  Video Annotator (VA) is a framework for annotating, managing, and iterating on video classification datasets. VA allows for a continuous annotation process, seamlessly integrating data collection and model training. VA achieves a median 6.8 point improvement in Average Precision relative to the most competitive baseline.
  arXiv  Detail & Related papers  (2024-02-09T17:19:05Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)

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.