Generative models for 3D object synthesis have seen significant advancements
with the incorporation of prior knowledge distilled from 2D diffusion models.
Nevertheless, challenges persist in the form of multi-view geometric
inconsistencies and slow generation speeds within the existing 3D synthesis
frameworks. This can be attributed to two factors: firstly, the deficiency of
abundant geometric a priori knowledge in optimization, and secondly, the
entanglement issue between geometry and texture in conventional 3D generation
methods.In response, we introduce MetaDreammer, a two-stage optimization
approach that leverages rich 2D and 3D prior knowledge. In the first stage, our
emphasis is on optimizing the geometric representation to ensure multi-view
consistency and accuracy of 3D objects. In the second stage, we concentrate on
fine-tuning the geometry and optimizing the texture, thereby achieving a more
refined 3D object. Through leveraging 2D and 3D prior knowledge in two stages,
respectively, we effectively mitigate the interdependence between geometry and
texture. MetaDreamer establishes clear optimization objectives for each stage,
resulting in significant time savings in the 3D generation process. Ultimately,
MetaDreamer can generate high-quality 3D objects based on textual prompts
within 20 minutes, and to the best of our knowledge, it is the most efficient
text-to-3D generation method. Furthermore, we introduce image control into the
process, enhancing the controllability of 3D generation. Extensive empirical
evidence confirms that our method is not only highly efficient but also
achieves a quality level that is at the forefront of current state-of-the-art
3D generation techniques.

MetaDreammer 是一种基于 2D 和 3D 先验知识的两阶段优化方法，通过在优化过程中分别使用 2D 和 3D 先验知识，有效减轻几何与纹理之间的相互依赖，从而在 3D 生成过程中节省时间并生成高质量的 3D 对象。与现有技术相比，MetaDreammer 是一种高效的文本到 3D 生成方法，并且还引入了图像控制来增强对 3D 生成过程的可控性。

MetaDreamer：高效文本生成三维模型的几何和纹理分离

MetaDreamer: Efficient Text-to-3D Creation With Disentangling Geometry  and Texture

Meta reinforcement learning (Meta RL) has been amply explored to quickly
learn an unseen task by transferring previously learned knowledge from similar
tasks. However, most state-of-the-art algorithms require the meta-training
tasks to have a dense coverage on the task distribution and a great amount of
data for each of them. In this paper, we propose MetaDreamer, a context-based
Meta RL algorithm that requires less real training tasks and data by doing
meta-imagination and MDP-imagination. We perform meta-imagination by
interpolating on the learned latent context space with disentangled properties,
as well as MDP-imagination through the generative world model where physical
knowledge is added to plain VAE networks. Our experiments with various
benchmarks show that MetaDreamer outperforms existing approaches in data
efficiency and interpolated generalization.

MetaDreamer 是一种基于上下文的元强化学习算法，通过元想象和 MDP 想象来减少实际训练任务和数据的需求，在学习未知任务时通过从类似任务中转移先前学习的知识，实验结果表明 MetaDreamer 在数据效率和插值推广方面胜过现有的方法。