Visual bridge helps control time series data for better forecasting
Image Synthesis as an Intermediate for Controllable Time Series Generation
Artificial Intelligence
Summary
Time series data, like stock prices or weather patterns, can be hard to generate correctly from just descriptions because the timing and patterns matter a lot. The authors created VisualBridge, which first turns these descriptions into pictures of the data, then uses those images to better capture and control key patterns like trends or seasonal changes. This makes the generated data more useful for predicting future events even when only a little real data is available. Their tests show this method helps forecasting tools learn better than usual data augmentation tricks.
What this means in practice
- •For forecasting software engineers: Create synthetic time series data with controlled patterns to improve forecasts when limited real data is available.
- •For financial data analysts: Generate realistic multivariate financial time series that reflect specific temporal behaviors for stress testing models.
Authors
Haochen Yuan, Jing Xie, Yunbo Wang
Abstract
Semantic-driven time-series generation offers a promising way to improve downstream learning in few-shot forecasting, but directly generating numerical sequences from language often fails to preserve the intended temporal structure. We propose VisualBridge, which uses time-series plots as a visual intermediate to bridge high-level temporal semantics and numerical sequences. An MLLM first converts plotted series into structured semantic representations, enabling explicit control over temporal properties such as trend, seasonality, and volatility. We then learn a semantic editing policy with downstream forecasting rewards, allowing the generation process to favor temporal patterns that are beneficial for the target task. The resulting sequences are further modeled by a temporal VAE to produce consistent multivariate augmentations. Experiments on standard public forecasting benchmarks demonstrate that VisualBridge improves few-shot forecasting over conventional augmentation methods, with ablations validating the roles of visual semantic grounding, learned semantic control, and VAE-based generation.