CineLOG: A Training Free Approach for Cinematic Long Video Generation
This work addresses the challenge of fine-grained control in video generation for applications in filmmaking and creative industries, though it is incremental as it builds on existing text-to-video methods with a new dataset and modular approach.
The authors tackled the problem of controllable video synthesis for cinematic attributes like camera trajectory and genre by introducing CineLOG, a dataset of 5,000 high-quality video clips with detailed annotations, and a pipeline that decouples text-to-video generation into stages; human evaluations showed their pipeline significantly outperforms state-of-the-art models in adhering to specific instructions while maintaining visual quality.
Controllable video synthesis is a central challenge in computer vision, yet current models struggle with fine grained control beyond textual prompts, particularly for cinematic attributes like camera trajectory and genre. Existing datasets often suffer from severe data imbalance, noisy labels, or a significant simulation to real gap. To address this, we introduce CineLOG, a new dataset of 5,000 high quality, balanced, and uncut video clips. Each entry is annotated with a detailed scene description, explicit camera instructions based on a standard cinematic taxonomy, and genre label, ensuring balanced coverage across 17 diverse camera movements and 15 film genres. We also present our novel pipeline designed to create this dataset, which decouples the complex text to video (T2V) generation task into four easier stages with more mature technology. To enable coherent, multi shot sequences, we introduce a novel Trajectory Guided Transition Module that generates smooth spatio-temporal interpolation. Extensive human evaluations show that our pipeline significantly outperforms SOTA end to end T2V models in adhering to specific camera and screenplay instructions, while maintaining professional visual quality. All codes and data are available at https://cine-log.pages.dev.