We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds. In contrast to many previous methods that are trained on small-scale datasets such as ShapeNet in a category-specific fashion, LRM adopts a highly scalable transformer-based architecture with 500 million learnable parameters to directly predict a neural radiance field (NeRF) from the input image. We train our model in an end-to-end manner on massive multi-view data containing around 1 million objects, including both synthetic renderings from Objaverse and real captures from MVImgNet. This combination of a high-capacity model and large-scale training data empowers our model to be highly generalizable and produce high-quality 3D reconstructions from various testing inputs including real-world in-the-wild captures and images from generative models. Video demos and interactable 3D meshes can be found on this website: https://yiconghong.me/LRM/.

翻译：我们提出了首个大规模重建模型（LRM），该模型能在5秒内从单张输入图像预测出物体的三维模型。与许多先前在ShapeNet等小规模数据集上以类别特定方式训练的方法不同，LRM采用高度可扩展的基于Transformer的架构，包含5亿可学习参数，可直接从输入图像预测神经辐射场（NeRF）。我们在包含约100万个物体的大规模多视角数据上以端到端方式训练模型，数据涵盖Objaverse的合成渲染图和MVImgNet的真实拍摄图。这种高容量模型与大规模训练数据的结合，使我们的模型具备高度泛化能力，能从包括真实世界野外拍摄和生成模型图像在内的多种测试输入中生成高质量三维重建。视频演示与可交互三维网格模型详见本网站：https://yiconghong.me/LRM/。