Following the tracking-by-attention paradigm, this paper introduces an object-centric, transformer-based framework for tracking in 3D. Traditional model-based tracking approaches incorporate the geometric effect of object- and ego motion between frames with a geometric motion model. Inspired by this, we propose S.T.A.R.-Track, which uses a novel latent motion model (LMM) to additionally adjust object queries to account for changes in viewing direction and lighting conditions directly in the latent space, while still modeling the geometric motion explicitly. Combined with a novel learnable track embedding that aids in modeling the existence probability of tracks, this results in a generic tracking framework that can be integrated with any query-based detector. Extensive experiments on the nuScenes benchmark demonstrate the benefits of our approach, showing state-of-the-art performance for DETR3D-based trackers while drastically reducing the number of identity switches of tracks at the same time.
Semantic scene completion is the task of jointly estimating 3D geometry and semantics of objects and surfaces within a given extent. This is a particularly challenging task on real-world data that is sparse and occluded. We propose a scene segmentation network based on local Deep Implicit Functions as a novel learning-based method for scene completion. Unlike previous work on scene completion, our method produces a continuous scene representation that is not based on voxelization. We encode raw point clouds into a latent space locally and at multiple spatial resolutions. A global scene completion function is subsequently assembled from the localized function patches. We show that this continuous representation is suitable to encode geometric and semantic properties of extensive outdoor scenes without the need for spatial discretization (thus avoiding the trade-off between level of scene detail and the scene extent that can be covered). We train and evaluate our method on semantically annotated LiDAR scans from the Semantic KITTI dataset. Our experiments verify that our method generates a powerful representation that can be decoded into a dense 3D description of a given scene. The performance of our method surpasses the state of the art on the Semantic KITTI Scene Completion Benchmark in terms of both geometric and semantic completion Intersection-over-Union (IoU).
This paper presents a novel CNN-based approach for synthesizing high-resolution LiDAR point cloud data. Our approach generates semantically and perceptually realistic results with guidance from specialized loss-functions. First, we utilize a modified per-point loss that addresses missing LiDAR point measurements. Second, we align the quality of our generated output with real-world sensor data by applying a perceptual loss. In large-scale experiments on real-world datasets, we evaluate both the geometric accuracy and semantic segmentation performance using our generated data vs. ground truth. In a mean opinion score testing we further assess the perceptual quality of our generated point clouds. Our results demonstrate a significant quantitative and qualitative improvement in both geometry and semantics over traditional non CNN-based up-sampling methods.
This paper presents a compact and accurate representation of 3D scenes that are observed by a LiDAR sensor and a monocular camera. The proposed method is based on the well-established Stixel model originally developed for stereo vision applications. We extend this Stixel concept to incorporate data from multiple sensor modalities. The resulting mid-level fusion scheme takes full advantage of the geometric accuracy of LiDAR measurements as well as the high resolution and semantic detail of RGB images. The obtained environment model provides a geometrically and semantically consistent representation of the 3D scene at a significantly reduced amount of data while minimizing information loss at the same time. Since the different sensor modalities are considered as input to a joint optimization problem, the solution is obtained with only minor computational overhead. We demonstrate the effectiveness of the proposed multimodal Stixel algorithm on a manually annotated ground truth dataset. Our results indicate that the proposed mid-level fusion of LiDAR and camera data improves both the geometric and semantic accuracy of the Stixel model significantly while reducing the computational overhead as well as the amount of generated data in comparison to using a single modality on its own.
Mobile robots and autonomous vehicles rely on multi-modal sensor setups to perceive and understand their surroundings. Aside from cameras, LiDAR sensors represent a central component of state-of-the-art perception systems. In addition to accurate spatial perception, a comprehensive semantic understanding of the environment is essential for efficient and safe operation. In this paper we present a novel deep neural network architecture called LiLaNet for point-wise, multi-class semantic labeling of semi-dense LiDAR data. The network utilizes virtual image projections of the 3D point clouds for efficient inference. Further, we propose an automated process for large-scale cross-modal training data generation called Autolabeling, in order to boost semantic labeling performance while keeping the manual annotation effort low. The effectiveness of the proposed network architecture as well as the automated data generation process is demonstrated on a manually annotated ground truth dataset. LiLaNet is shown to significantly outperform current state-of-the-art CNN architectures for LiDAR data. Applying our automatically generated large-scale training data yields a boost of up to 14 percentage points compared to networks trained on manually annotated data only.
Recent progress in advanced driver assistance systems and the race towards autonomous vehicles is mainly driven by two factors: (1) increasingly sophisticated algorithms that interpret the environment around the vehicle and react accordingly, and (2) the continuous improvements of sensor technology itself. In terms of cameras, these improvements typically include higher spatial resolution, which as a consequence requires more data to be processed. The trend to add multiple cameras to cover the entire surrounding of the vehicle is not conducive in that matter. At the same time, an increasing number of special purpose algorithms need access to the sensor input data to correctly interpret the various complex situations that can occur, particularly in urban traffic. By observing those trends, it becomes clear that a key challenge for vision architectures in intelligent vehicles is to share computational resources. We believe this challenge should be faced by introducing a representation of the sensory data that provides compressed and structured access to all relevant visual content of the scene. The Stixel World discussed in this paper is such a representation. It is a medium-level model of the environment that is specifically designed to compress information about obstacles by leveraging the typical layout of outdoor traffic scenes. It has proven useful for a multitude of automotive vision applications, including object detection, tracking, segmentation, and mapping. In this paper, we summarize the ideas behind the model and generalize it to take into account multiple dense input streams: the image itself, stereo depth maps, and semantic class probability maps that can be generated, e.g., by CNNs. Our generalization is embedded into a novel mathematical formulation for the Stixel model. We further sketch how the free parameters of the model can be learned using structured SVMs.
Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes. To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recorded in streets from 50 different cities. 5000 of these images have high quality pixel-level annotations; 20000 additional images have coarse annotations to enable methods that leverage large volumes of weakly-labeled data. Crucially, our effort exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Our accompanying empirical study provides an in-depth analysis of the dataset characteristics, as well as a performance evaluation of several state-of-the-art approaches based on our benchmark.