3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation

arXiv:2403.09439v1 Announce Type: new
Abstract: Text-driven 3D scene generation techniques have made rapid progress in recent years. Their success is mainly attributed to using existing generative models to iteratively perform image warping and inpainting to generate 3D scenes. However, these methods heavily rely on the outputs of existing models, leading to error accumulation in geometry and appearance that prevent the models from being used in various scenarios (e.g., outdoor and unreal scenarios). To address this limitation, we generatively refine the …

3d scene generation 3d scenes abstract arxiv consistent cs.ai cs.cv error generate generative generative models geometry however image inpainting progress success text type