Recent developments in intelligent robot systems, especially autonomous vehicles, put forward higher requirements for safety and comfort. Road conditions are crucial factors affecting the comprehensive performance of ground vehicles. Nonetheless, existing environment perception datasets for autonomous driving lack attention to road surface areas. In this paper, we introduce the road surface reconstruction dataset, providing multi-modal, high-resolution, and high-precision data collected by real-vehicle platform in diverse driving conditions. It covers common road types containing approximately 16,000 pairs of stereo images, point clouds, and ground-truth depth/disparity maps, with accurate data processing pipelines to ensure its quality. Preliminary evaluations reveal the effectiveness of our dataset and the challenge of the task, underscoring substantial opportunities of it as a valuable resource for advancing computer vision techniques. The reconstructed road structure and texture contribute to the analysis and prediction of vehicle responses for motion planning and control systems.

Human physical scene understanding requires more than simply localizing and recognizing objects Ñ we can quickly adapt our predictions about how a scene will unfold by incorporating objects' latent physics properties, such as the masses of the objects in the scene. What are the underlying computational mechanisms that allow humans to infer these physical properties and adapt their physical predictions so efficiently from visual inputs? One hypothesis is that general intuitive physics knowledge can be learned from enough raw data, instantiated as computational models that predict future video frames in large datasets of complex scenes. To test this hypothesis, we evaluate existing state-of-the-art video models. We measured both model and human performance on Physion++, a novel dataset and benchmark that rigorously evaluates visual physical prediction in humans and machines, under circumstances where accurate physical prediction relies on accurate estimates of the latent physical properties of objects in the scene. Specifically, we tested scenarios where accurate prediction relied on accurate estimates of objects' mechanical properties, including masses, friction, elasticity and deformability, and the values of these mechanical properties could only be inferred by observing how these objects moved and interacted with other objects and/or fluids. We found that models that encode objectness and physical states tend to perform better, yet there is still a huge gap compared to human performance. We also found most models' predictions correlate poorly with that made by humans. These results show that current deep learning models that succeed in some settings nevertheless fail to achieve human-level physical prediction in other cases, especially those where latent property inference is required.