ROM_S01: Original and AI-Generated Video Scenes for Style Analysis
by Jinyu Kim·Updated 2d ago
78.4 MB24files
Available on 1 platform
Sign in to view source links and access this dataset
Description
Jinyu Kim's doctoral dissertation project provides scene-level video materials from the 1945 Italian Neorealist film 'Rome, Open City' by Roberto Rossellini. The 78.4 MB dataset includes RAW and PRE-processed MP4 videos, prompt files, generation settings, and metadata records for comparative analysis of original and AI-generated content. PRE files are standardized at 720p, 24 fps, and 8 seconds, with audio excluded from analysis.
Use Cases
Comparative analysis of film style between original and AI-generated videos based on scene-level materials.
Training or evaluating generative AI video models based on provided prompts and generation settings.
Studying the reconfiguration of Italian Neorealist aesthetics through AI based on the described film and style.
Benchmarking video preprocessing and standardization techniques based on the 720p, 24 fps, 8-second PRE files.
Strengths
Includes both RAW generated videos and standardized PRE videos at 720p, 24 fps, and 8 seconds.
Contains associated prompt files and generation settings, providing context for the AI-generated content.
Focuses on a specific, well-defined film ('Rome, Open City', 1945) and style (Italian Neorealism).
Limitations
Row count is unknown, which may limit suitability assessment.
Column-level documentation is absent; field semantics must be inferred after download.
Audio is excluded from the analysis, limiting multimodal study.
Provenance
Source
Part of a doctoral dissertation project by Jinyu Kim, shared on figshare.
Collection Method
Likely created by processing scenes from the film 'Rome, Open City' and generating corresponding AI video versions.
Time Range
The source film is from 1945; the dataset creation date is not specified.
Freshness
Last updated 2026-06-04 21:04:14; freshness should be verified.
Geography
The film 'Rome, Open City' is set in Rome, Italy.
License is CC-BY-4.0. The dataset is relatively small at 78.4 MB.