AI RESEARCH

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

arXiv CS.CV

ArXi:2604.13730v1 Announce Type: new 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 nstrate that existing text-to-3D models suffer from catastrophic forgetting under incremental