ReConText3D: Replay-based Continual Text-to-3D Generation

TL;DR

ReConText3D introduces a novel continual learning framework for text-to-3D generation, effectively mitigating catastrophic forgetting and enabling incremental learning of new 3D categories from textual descriptions.

Contribution

It is the first to address continual learning in text-to-3D generation, proposing a replay memory method and a new benchmark for systematic evaluation.

Findings

ReConText3D outperforms baselines on the Toys4K-CL benchmark.

The method preserves old knowledge while learning new 3D categories.

A new benchmark for incremental text-to-3D learning is introduced.

Abstract

Continual learning enables models to acquire new knowledge over time while retaining previously learned capabilities. However, its application to text-to-3D generation remains unexplored. We present ReConText3D, the first framework for continual text-to-3D generation. We first demonstrate that existing text-to-3D models suffer from catastrophic forgetting under incremental training. ReConText3D enables generative models to incrementally learn new 3D categories from textual descriptions while preserving the ability to synthesize previously seen assets. Our method constructs a compact and diverse replay memory through text-embedding k-Center selection, allowing representative rehearsal of prior knowledge without modifying the underlying architecture. To systematically evaluate continual text-to-3D learning, we introduce Toys4K-CL, a benchmark derived from the Toys4K dataset that provides balanced and semantically diverse class-incremental splits. Extensive experiments on the Toys4K-CL benchmark show that ReConText3D consistently outperforms all baselines across different generative backbones, maintaining high-quality generation for both old and new classes. To the best of our knowledge, this work establishes the first continual learning framework and benchmark for text-to-3D generation, opening a new direction for incremental 3D generative modeling. Project page is available at: https://mauk95.github.io/ReConText3D/.