Scaling up representations for images or text has been extensively
investigated in the past few years and has led to revolutions in learning
vision and language. However, scalable representation for 3D objects and scenes
is relatively unexplored. In this work, we present Uni3D, a 3D foundation model
to explore the unified 3D representation at scale. Uni3D uses a 2D initialized
ViT end-to-end pretrained to align the 3D point cloud features with the
image-text aligned features. Via the simple architecture and pretext task,
Uni3D can leverage abundant 2D pretrained models as initialization and
image-text aligned models as the target, unlocking the great potential of 2D
models and scaling-up strategies to the 3D world. We efficiently scale up Uni3D
to one billion parameters, and set new records on a broad range of 3D tasks,
such as zero-shot classification, few-shot classification, open-world
understanding and part segmentation. We show that the strong Uni3D
representation also enables applications such as 3D painting and retrieval in
the wild. We believe that Uni3D provides a new direction for exploring both
scaling up and efficiency of the representation in 3D domain.

通过 Uni3D，我们提出了一种可扩展的 3D 对象和场景表示方法，利用 2D 模型作为初始化，并通过图像 - 文本对齐模型作为目标，解锁了 2D 模型和扩展策略在 3D 世界中的潜力，并在许多 3D 任务中取得了新的成绩，如零样本分类、少样本分类、开放世界理解和部分分割，并展示了 Uni3D 在野外环境中进行的 3D 绘画和检索等应用。我们相信，Uni3D 为探索 3D 领域的表示扩展和效率提供了新的方向。