# Generative Spatiotemporal Data Augmentation

Source: [Generative Spatiotemporal Data Augmentation](<https://www.sota2.com/research/paper/6940e775456146936284f64f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-17T05:03:45.767Z

Authors: Jinfan Zhou, Lixin Luo, Sungmin Eum, Heesung Kwon, Jeong Joon Park

Published: 2025-12-14T01:18:48.000Z

## Abstract

We explore spatiotemporal data augmentation using video foundation models to diversify both camera viewpoints and scene dynamics. Unlike existing approaches based on simple geometric transforms or appearance perturbations, our method leverages off-the-shelf video diffusion models to generate realistic 3D spatial and temporal variations from a given image dataset. Incorporating these synthesized video clips as supplemental training data yields consistent performance gains in low-data settings, such as UAV-captured imagery where annotations are scarce. Beyond empirical improvements, we provide practical guidelines for (i) choosing an appropriate spatiotemporal generative setup, (ii) transferring annotations to synthetic frames, and (iii) addressing disocclusion - regions newly revealed and unlabeled in generated views. Experiments on COCO subsets and UAV-captured datasets show that, when applied judiciously, spatiotemporal augmentation broadens the data distribution along axes underrepresented by traditional and prior generative methods, offering an effective lever for improving model performance in data-scarce regimes.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on COCO 5k](<https://www.sota2.com/research/sota/object-detection-on-coco-5k.md>): Object Detection; COCO 5k; mAP@50: 42.6.

- [Object Detection on Semantic Drone (remaining 100 images)](<https://www.sota2.com/research/sota/object-detection-on-semantic-drone-remaining-100-images.md>): Object Detection; Semantic Drone (remaining 100 images); mAP@50: 90.7.

- [Object Detection on Semantic Drone](<https://www.sota2.com/research/sota/object-detection-on-semantic-drone.md>): Object Detection; Semantic Drone; mAP@50: 87.4.

- [Object Detection on VisDrone](<https://www.sota2.com/research/sota/object-detection-on-visdrone.md>): Object Detection; VisDrone; mAP50: 49.6.

- [Object Detection on COCO 2017 (val)](<https://www.sota2.com/research/sota/object-detection-on-coco-2017-val.md>): Object Detection; COCO 2017 (val); AP: 34.2.

- [Object Detection on COCO (val)](<https://www.sota2.com/research/sota/object-detection-on-coco-val.md>): Object Detection; COCO (val); mAP: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.12508>)

[PDF](<https://arxiv.org/pdf/2512.12508.pdf>)