For the last few decades, several major subfields of artificial intelligence including computer
vision, graphics, and robotics have progressed largely independently from each other …

MonoScene proposes a 3D Semantic Scene Completion (SSC) framework, where the dense
geometry and semantics of a scene are inferred from a single monocular RGB image …

The ability to learn richer network representations generally boosts the performance of deep
learning models. To improve representation-learning in convolutional neural networks, we …

Enhancing the generalization capability of deep neural networks to unseen domains is
crucial for safety-critical applications in the real world such as autonomous driving. To …

Convolution exploits locality for efficiency at a cost of missing long range context. Self-
attention has been adopted to augment CNNs with non-local interactions. Recent works …

In this paper, we study the context aggregation problem in semantic segmentation.
Motivated by that the label of a pixel is the category of the object that the pixel belongs to, we …

Camera and lidar are important sensor modalities for robotics in general and self-driving
cars in particular. The sensors provide complementary information offering an opportunity for …

The performance of video prediction has been greatly boosted by advanced deep neural
networks. However, most of the current methods suffer from large model sizes and require …

In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic
segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve …

Semantic segmentation models based on convolutional neural networks have recently
displayed remarkable performance for a multitude of applications. However, these models …