3D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable Editing
This work provides a flexible augmentation approach to enhance 3D data diversity for scene understanding tasks, though it is incremental as it builds on existing generative models.
The authors tackled the problem of limited diversity in 3D training data by proposing a method to automatically generate synthetic 3D labeled data using pretrained diffusion models and ChatGPT, enabling substantial data production without real data to address few-shot learning and class imbalances.
Data augmentation plays a crucial role in deep learning, enhancing the generalization and robustness of learning-based models. Standard approaches involve simple transformations like rotations and flips for generating extra data. However, these augmentations are limited by their initial dataset, lacking high-level diversity. Recently, large models such as language models and diffusion models have shown exceptional capabilities in perception and content generation. In this work, we propose a new paradigm to automatically generate 3D labeled training data by harnessing the power of pretrained large foundation models. For each target semantic class, we first generate 2D images of a single object in various structure and appearance via diffusion models and chatGPT generated text prompts. Beyond texture augmentation, we propose a method to automatically alter the shape of objects within 2D images. Subsequently, we transform these augmented images into 3D objects and construct virtual scenes by random composition. This method can automatically produce a substantial amount of 3D scene data without the need of real data, providing significant benefits in addressing few-shot learning challenges and mitigating long-tailed class imbalances. By providing a flexible augmentation approach, our work contributes to enhancing 3D data diversity and advancing model capabilities in scene understanding tasks.