LiDAR Semantic Segmentation is a fundamental task in autonomous driving perception consisting of associating each LiDAR point to a semantic label. Fully-supervised models have widely tackled this task, but they require labels for each scan, which either limits their domain or requires impractical amounts of expensive annotations.Camera images, which are generally recorded alongside LiDAR pointclouds, can be processed by the widely available 2D foundation models, which are generic and dataset-agnostic. However, distilling knowledge from 2D data to improve LiDAR perception raises domain adaptation challenges. For example, the classical perspective projection suffers from the parallax effect produced by the position shift between both sensors at their respective capture times.We propose a Semi-Supervised Learning setup to leverage unlabeled LiDAR pointclouds alongside distilled knowledge from the camera images. To self-supervise our model on the unlabeled scans, we add an auxiliary NeRF head and cast rays from the camera viewpoint over the unlabeled voxel features. The NeRF head predicts densities and semantic logits at each sampled ray location which are used for rendering pixel semantics. Concurrently, we query the Segment-Anything (SAM) foundation model with the camera image to generate a set of unlabeled generic masks. We fuse the masks with the rendered pixel semantics from LiDAR to produce pseudo-labels that supervise the pixel predictions. During inference, we drop the NeRF head and run our model with only LiDAR.We show the effectiveness of our approach in three public LiDAR Semantic Segmentation benchmarks: nuScenes, SemanticKITTI and ScribbleKITTI.

Panoptic segmentation of point clouds is one of the key challenges of 3D scene understanding, requiring the simultaneous prediction of semantics and object instances. Tasks like autonomous driving strongly depend on these information to get a holistic understanding of their 3D environment. This work presents a novel proposal free framework for lidar-based panoptic segmentation, which exploits three different point cloud representations, leveraging their strengths and compensating their weaknesses. The efficient projection-based range view and bird's eye view are combined and further extended by a point-based network with a novel attention-based neighborhood aggregation for improved semantic features. Cluster-based object recognition in bird's eye view enables an efficient and high-quality instance segmentation. Semantic and instance segmentation are fused and further refined by a novel instance classification for the final panoptic segmentation. The results on two challenging large-scale datasets, nuScenes and SemanticKITTI, show the success of the proposed framework, which outperforms all existing approaches on nuScenes and achieves state-of-the-art results on SemanticKITTI.

Robust environment perception for autonomous vehicles is a tremendous challenge, which makes a diverse sensor set with e.g. camera, lidar and radar crucial. In the process of understanding the recorded sensor data, 3D semantic segmentation plays an important role. Therefore, this work presents a pyramid-based deep fusion architecture for lidar and camera to improve 3D semantic segmentation of traffic scenes. Individual sensor backbones extract feature maps of camera images and lidar point clouds. A novel Pyramid Fusion Backbone fuses these feature maps at different scales and combines the multimodal features in a feature pyramid to compute valuable multimodal, multi-scale features. The Pyramid Fusion Head aggregates these pyramid features and further refines them in a late fusion step, incorporating the final features of the sensor backbones. The approach is evaluated on two challenging outdoor datasets and different fusion strategies and setups are investigated. It outperforms recent range view based lidar approaches as well as all so far proposed fusion strategies and architectures.

Understanding and interpreting a 3d environment is a key challenge for autonomous vehicles. Semantic segmentation of 3d point clouds combines 3d information with semantics and thereby provides a valuable contribution to this task. In many real-world applications, point clouds are generated by lidar sensors in a consecutive fashion. Working with a time series instead of single and independent frames enables the exploitation of temporal information. We therefore propose a recurrent segmentation architecture (RNN), which takes a single range image frame as input and exploits recursively aggregated temporal information. An alignment strategy, which we call Temporal Memory Alignment, uses ego motion to temporally align the memory between consecutive frames in feature space. A Residual Network and ConvGRU are investigated for the memory update. We demonstrate the benefits of the presented approach on two large-scale datasets and compare it to several state of-the-art methods. Our approach ranks first on the SemanticKITTI [4] multiple scan benchmark and achieves state-of-the-art performance on the single scan benchmark. In addition, the evaluation shows that the exploitation of temporal information significantly improves segmentation results compared to a single frame approach.

We present a reinforcement learning approach using Deep Q-Networks to steer a vehicle in a 3D physics simulation. Relying solely on camera image input the approach directly learns steering the vehicle in an end-to-end manner. The system is able to learn human driving behavior without the need of any labeled training data. An action-based reward function is proposed, which is motivated by a potential use in real world reinforcement learning scenarios. Compared to a naive distance-based reward function, it improves the overall driving behavior of the vehicle agent. The agent is even able to reach comparable to human driving performance on a previously unseen track in our simulation environment.