Introduces KathaTrace protocol and KathaBench-25K benchmark to quantify Semantic Trajectory Gap (STG) as the loss of transition meaning in visualized narratives, reporting STG of 23.5 +/- 1.3 across generators.
Vistorybench: Comprehensive benchmark suite for story visualization
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
fields
cs.CV 8years
2026 8representative citing papers
MSAVBench is the first comprehensive benchmark for multi-shot audio-video generation featuring four dimensions, challenging scenarios, and an adaptive hybrid evaluation framework that achieves 91.5% Spearman correlation with human judgments.
CutVerse benchmark evaluates GUI agents on 186 complex media post-production tasks in seven apps and reports 36% success rate for existing models.
Crayotter, a multimodal multi-agent video editor that exposes every planning and tool step, scored 3.40/5 in human evaluation on 23 themes, beating two baselines (2.44 and 1.70).
StoryBlender generates inter-shot consistent editable 3D storyboards using a three-stage pipeline of semantic-spatial grounding, canonical asset materialization, and spatial-temporal dynamics with agent-based verification.
A hierarchical multi-agent framework converts a single sentence into a short drama using debate-based scripting, 3D-grounded first frames for spatial consistency, and multi-stage reviewer loops.
DreamShot generates controllable multi-shot storyboards from text or character references by exploiting video diffusion priors and a Role-Attention Consistency Loss.
citing papers explorer
-
KathaTrace: Diagnosing Semantic Trajectory Collapse in Generated Visual Narratives
Introduces KathaTrace protocol and KathaBench-25K benchmark to quantify Semantic Trajectory Gap (STG) as the loss of transition meaning in visualized narratives, reporting STG of 23.5 +/- 1.3 across generators.
-
MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
MSAVBench is the first comprehensive benchmark for multi-shot audio-video generation featuring four dimensions, challenging scenarios, and an adaptive hybrid evaluation framework that achieves 91.5% Spearman correlation with human judgments.
-
CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing
CutVerse benchmark evaluates GUI agents on 186 complex media post-production tasks in seven apps and reports 36% success rate for existing models.
-
Crayotter: Traceable Multi-Agent Workflows for Long-Form Video Editing
Crayotter, a multimodal multi-agent video editor that exposes every planning and tool step, scored 3.40/5 in human evaluation on 23 themes, beating two baselines (2.44 and 1.70).
-
StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics
StoryBlender generates inter-shot consistent editable 3D storyboards using a three-stage pipeline of semantic-spatial grounding, canonical asset materialization, and spatial-temporal dynamics with agent-based verification.
-
One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems
A hierarchical multi-agent framework converts a single sentence into a short drama using debate-based scripting, 3D-grounded first frames for spatial consistency, and multi-stage reviewer loops.
-
DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior
DreamShot generates controllable multi-shot storyboards from text or character references by exploiting video diffusion priors and a Role-Attention Consistency Loss.
- MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation