相关论文: EntityBench: Towards Entity-Consistent Long-Range …
Maintaining consistent characters, props, and environments across multiple shots is a central challenge in narrative video generation. Existing models can produce high-quality short clips but often fail to preserve entity identity and…
Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific text prompts. Recent autoregressive methods reuse previously generated frames as memory.…
The evolution of video generation toward complex, multi-shot narratives has exposed a critical deficit in current evaluation methods. Existing benchmarks remain anchored to single-shot paradigms, lacking the comprehensive story assets and…
Visual storytelling requires generating multi-shot videos with cinematic quality and long-range consistency. Inspired by human memory, we propose StoryMem, a paradigm that reformulates long-form video storytelling as iterative shot…
Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst being consistent throughout the frames. Creating a benchmark…
Long-form video generation is rapidly moving from short, single-scene synthesis toward minute-long, multi-shot creation with narrative structure, cinematic control, audio, and cross-modal synchronization. However, evaluating such videos…
Recent advancements in video generation models, like Stable Video Diffusion, show promising results, but primarily focus on short, single-scene videos. These models struggle with generating long videos that involve multiple scenes, coherent…
Generation of images containing multiple humans, performing complex actions, while preserving their facial identities, is a significant challenge. A major factor contributing to this is the lack of a dedicated benchmark. To address this, we…
Text-to-video (T2V) generation models have made significant progress in creating visually appealing videos. However, they struggle with generating coherent sequential narratives that require logical progression through multiple events.…
Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background…
The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed evaluation operators…
Counting in long videos remains a fundamental yet underexplored challenge in computer vision. Real-world recordings often span tens of minutes or longer and contain sparse, diverse events, making long-range temporal reasoning particularly…
Video foundation models aim to integrate video understanding, generation, editing, and instruction following within a single framework, making them a central direction for next-generation multimodal systems. However, existing evaluation…
Video generation is rapidly evolving from single-shot synthesis to complex multi-shot audio-video (MSAV) narratives to meet real-world demands. However, evaluating such frontier models remains a fundamental challenge. Existing benchmarks…
Story visualization aims to generate coherent image sequences that faithfully represent a narrative and match given character references. Despite progress in generative models, existing benchmarks remain narrow in scope, often limited to…
Entity state tracking is a necessary component of world modeling that requires maintaining coherent representations of entities over time. Previous work has benchmarked entity tracking performance in purely text-based tasks. We introduce…
Video generation has advanced rapidly, with recent methods producing increasingly convincing animated results. However, existing benchmarks-largely designed for realistic videos-struggle to evaluate animation-style generation with its…
Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align…
Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align…
Evaluating generative video models remains an open problem. Reference-based metrics such as Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) reward pixel fidelity over semantic correctness, while Frechet…