DynamicEval: Rethinking Evaluation for Dynamic Text-to-Video Synthesis

• URL: http://arxiv.org/abs/2510.07441v1
• Date: Wed, 08 Oct 2025 18:41:04 GMT
• Title: DynamicEval: Rethinking Evaluation for Dynamic Text-to-Video Synthesis
• Authors: Nithin C. Babu, Aniruddha Mahapatra, Harsh Rangwani, Rajiv Soundararajan, Kuldeep Kulkarni,
• Abstract summary: Existing text-to-video (T2V) evaluation benchmarks, such as VBench and EvalCrafter, suffer from two limitations.<n>We introduce DynamicEval, a benchmark consisting of systematically curated prompts emphasizing dynamic camera motion.<n>For background scene consistency, we obtain the interpretable error maps based on the Vbench motion smoothness metric.<n>Our proposed metrics achieve stronger correlations with human preferences at both the video level and the model level.
• Score: 17.750053029702222
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Existing text-to-video (T2V) evaluation benchmarks, such as VBench and EvalCrafter, suffer from two limitations. (i) While the emphasis is on subject-centric prompts or static camera scenes, camera motion essential for producing cinematic shots and existing metrics under dynamic motion are largely unexplored. (ii) These benchmarks typically aggregate video-level scores into a single model-level score for ranking generative models. Such aggregation, however, overlook video-level evaluation, which is vital to selecting the better video among the candidate videos generated for a given prompt. To address these gaps, we introduce DynamicEval, a benchmark consisting of systematically curated prompts emphasizing dynamic camera motion, paired with 45k human annotations on video pairs from 3k videos generated by ten T2V models. DynamicEval evaluates two key dimensions of video quality: background scene consistency and foreground object consistency. For background scene consistency, we obtain the interpretable error maps based on the Vbench motion smoothness metric. We observe that while the Vbench motion smoothness metric shows promising alignment with human judgments, it fails in two cases: occlusions/disocclusions arising from camera and foreground object movements. Building on this, we propose a new background consistency metric that leverages object error maps to correct two failure cases in a principled manner. Our second innovation is the introduction of a foreground consistency metric that tracks points and their neighbors within each object instance to assess object fidelity. Extensive experiments demonstrate that our proposed metrics achieve stronger correlations with human preferences at both the video level and the model level (an improvement of more than 2% points), establishing DynamicEval as a more comprehensive benchmark for evaluating T2V models under dynamic camera motion.

Related papers

• Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding [54.859943475818234]
  We present Motion4D, a novel framework that integrates 2D priors from foundation models into a unified 4D Gaussian Splatting representation.<n>Our method features a two-part iterative optimization framework: 1) Sequential optimization, which updates motion and semantic fields in consecutive stages to maintain local consistency, and 2) Global optimization, which jointly refines all attributes for long-term coherence.<n>Our method significantly outperforms both 2D foundation models and existing 3D-based approaches across diverse scene understanding tasks, including point-based tracking, video object segmentation, and novel view synthesis.
  arXiv  Detail & Related papers  (2025-12-03T09:32:56Z)
• VideoScore2: Think before You Score in Generative Video Evaluation [69.43069741467603]
  VideoScore2 is a multi-dimensional, interpretable, and human-aligned framework that explicitly evaluates visual quality, text-to-video alignment, and physical/common-sense consistency.<n>Our model is trained on a large-scale dataset VideoFeedback2 containing 27,168 human-annotated videos.
  arXiv  Detail & Related papers  (2025-09-26T18:09:03Z)
• SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation [56.90807453045657]
  SynMotion is a motion-customized video generation model that jointly leverages semantic guidance and visual adaptation.<n>At the semantic level, we introduce the dual-em semantic comprehension mechanism which disentangles subject and motion representations.<n>At the visual level, we integrate efficient motion adapters into a pre-trained video generation model to enhance motion fidelity and temporal coherence.
  arXiv  Detail & Related papers  (2025-06-30T10:09:32Z)
• VMBench: A Benchmark for Perception-Aligned Video Motion Generation [22.891770315274346]
  We introduce VMBench, a comprehensive Video Motion Benchmark.<n>VMBench has perception-aligned motion metrics and features the most diverse types of motion.<n>This is the first time that the quality of motion in videos has been evaluated from the perspective of human perception alignment.
  arXiv  Detail & Related papers  (2025-03-13T05:54:42Z)
• Evaluation of Text-to-Video Generation Models: A Dynamics Perspective [94.2662603491163]
  Existing evaluation protocols primarily focus on temporal consistency and content continuity. We propose an effective evaluation protocol, termed DEVIL, which centers on the dynamics dimension to evaluate T2V models.
  arXiv  Detail & Related papers  (2024-07-01T08:51:22Z)
• Improving Unsupervised Video Object Segmentation with Motion-Appearance Synergy [52.03068246508119]
  We present IMAS, a method that segments the primary objects in videos without manual annotation in training or inference. IMAS achieves Improved UVOS with Motion-Appearance Synergy. We demonstrate its effectiveness in tuning critical hyperparams previously tuned with human annotation or hand-crafted hyperparam-specific metrics.
  arXiv  Detail & Related papers  (2022-12-17T06:47:30Z)
• Learning to Segment Rigid Motions from Two Frames [72.14906744113125]
  We propose a modular network, motivated by a geometric analysis of what independent object motions can be recovered from an egomotion field. It takes two consecutive frames as input and predicts segmentation masks for the background and multiple rigidly moving objects, which are then parameterized by 3D rigid transformations. Our method achieves state-of-the-art performance for rigid motion segmentation on KITTI and Sintel.
  arXiv  Detail & Related papers  (2021-01-11T04:20:30Z)
• Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos [96.45804577283563]
  We present a novel hybrid dynAmic-static Context-aware attenTION NETwork (ACTION-NET) for action assessment in long videos. We learn the video dynamic information but also focus on the static postures of the detected athletes in specific frames. We combine the features of the two streams to regress the final video score, supervised by ground-truth scores given by experts.
  arXiv  Detail & Related papers  (2020-08-13T15:51:42Z)

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.