Pith. sign in

REVIEW 15 cited by

UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.13691 v1 pith:67JZNSUP submitted 2025-06-16 cs.CV

UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions

classification cs.CV
keywords videohigh-qualitydatasetgenerationtextitultravideocaptionsdata
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. The growing demand for video applications sets higher requirements for high-quality video generation models. For example, the generation of movie-level Ultra-High Definition (UHD) videos and the creation of 4K short video content. However, the existing public datasets cannot support related research and applications. In this paper, we first propose a high-quality open-sourced UHD-4K (22.4\% of which are 8K) text-to-video dataset named UltraVideo, which contains a wide range of topics (more than 100 kinds), and each video has 9 structured captions with one summarized caption (average of 824 words). Specifically, we carefully design a highly automated curation process with four stages to obtain the final high-quality dataset: \textit{i)} collection of diverse and high-quality video clips. \textit{ii)} statistical data filtering. \textit{iii)} model-based data purification. \textit{iv)} generation of comprehensive, structured captions. In addition, we expand Wan to UltraWan-1K/-4K, which can natively generate high-quality 1K/4K videos with more consistent text controllability, demonstrating the effectiveness of our data curation.We believe that this work can make a significant contribution to future research on UHD video generation. UltraVideo dataset and UltraWan models are available at https://xzc-zju.github.io/projects/UltraVideo.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection

    cs.CV 2025-12 conditional novelty 8.0

    RobustSora benchmark demonstrates that current AI video detectors rely heavily on visible watermarks, with average accuracy drops of 6.6 percentage points when watermarks are erased and increased false alarms when wat...

  2. VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset

    cs.CV 2026-05 unverdicted novelty 7.0

    VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.

  3. SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control

    cs.CV 2026-05 unverdicted novelty 6.0

    SmartDirector generates cinematic videos via Director-Gen for low-res keyframe-conditioned output followed by Director-SR refinement using high-res keyframes, trained on curated movie sequences.

  4. AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling

    cs.CV 2026-05 unverdicted novelty 6.0

    AtlasVid proposes a decoupled global-local diffusion framework that trains at low resolution with LoRA and generalizes to ultra-high-resolution long video synthesis via semantic proxy guidance and locality-preserving ...

  5. SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    SwiftI2V matches end-to-end 2K I2V quality on VBench while cutting GPU time by 202x via conditional segment-wise generation that bounds token cost and preserves input fidelity.

  6. SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    SwiftI2V achieves comparable 2K I2V quality to end-to-end models on VBench-I2V while cutting GPU time by 202x through low-resolution motion planning followed by strongly image-conditioned segment-wise high-resolution ...

  7. Building a Precise Video Language with Human-AI Oversight

    cs.CV 2026-04 unverdicted novelty 6.0

    CHAI framework pairs AI pre-captions with expert human critiques to produce precise video descriptions, enabling open models to outperform closed ones like Gemini-3.1-Pro and improve fine-grained control in video gene...

  8. From Ideal to Real: Stable Video Object Removal under Imperfect Conditions

    cs.CV 2026-03 unverdicted novelty 6.0

    SVOR achieves stable, shadow-free video object removal under real-world imperfections via MUSE mask handling, DA-Seg localization, and curriculum training on real and synthetic data.

  9. MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment

    cs.CV 2026-07 unverdicted novelty 5.0

    MoVA introduces modular asymmetric dual projections to handle temporal misalignment and semantic asymmetry in long video-text alignment.

  10. Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation

    cs.CV 2026-06 unverdicted novelty 5.0

    Shell-LCC models the high-quality data manifold as an isotropic shell to derive cost-free reward signals that improve realism and high-frequency details in text-to-video generation.

  11. Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control

    cs.CV 2026-06 unverdicted novelty 5.0

    A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.

  12. CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation

    cs.CV 2026-06 unverdicted novelty 5.0

    Introduces CineDance-1M dataset for multi-shot long-form text-to-audio-video generation along with CineBench and a model adaptation.

  13. Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions

    cs.CV 2026-06 unverdicted novelty 5.0

    Ultra Flash introduces a cascaded streaming super-resolution framework with specialized training, upsampling, and optimization to enable real-time high-resolution video generation from low-res diffusion models.

  14. Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching

    cs.CV 2026-06 unverdicted novelty 5.0

    ByG enables unpaired training of flow matching editing models by pairing self-extracted instruction-following cues with cycle-consistency and routing gradients from clean predictions to noisy states.

  15. PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset

    cs.CV 2026-05 unverdicted novelty 5.0

    PixVerve introduces a 95K ultra-high-resolution image-text dataset and training strategies that enable native 100-megapixel text-to-image generation together with a new evaluation benchmark.