MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning

Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods either rely on expensive supervised learning with 3D annotations, limiting the scalability, or focus on single-frame or monocular inputs, neglecting the temporal information, which is fundamental for the ultimate application, i.e., end-to-end planning. We propose MIM4D, a novel pre-training paradigm based on dual masked image modeling (MIM). MIM4D leverages both spatial and temporal relations by training on masked multi-view video inputs. It constructs pseudo-3D features using continuous scene flow and projects them onto 2D plane for supervision. To address the lack of dense 3D supervision, MIM4D reconstruct pixels by employing 3D volumetric differentiable rendering to learn geometric representations. We demonstrate that MIM4D achieves state-of-the-art performance on the nuScenes dataset for visual representation learning in autonomous driving. It significantly improves existing methods on multiple downstream tasks, including end-to-end planning(\(9\%\) collision decrease), BEV segmentation (\(8.7\%\) IoU), 3D object detection (\(3.5\%\) mAP), and HD map construction (\(1.4\%\) mAP). Our work offers a new choice for learning representation at scale in autonomous driving. Code and models are released at https://github.com/hustvl/MIM4D.