Autonomous vehicles often have varying camera sensor setups, which is inevitable due to restricted placement options for different vehicle types. Training a perception model on one particular setup and evaluating it on a new, different sensor setup reveals the so-called cross-sensor domain gap, typically leading to a degradation in accuracy. In this paper, we investigate the impact of the cross-sensor domain gap on state-of-the-art 3D object detectors. To this end, we introduce CamShift, a dataset inspired by nuScenes and created in CARLA to specifically simulate the domain gap between subcompact vehicles and sport utility vehicles (SUVs). Using CamShift, we demonstrate significant cross-sensor performance degradation, identify robustness dependencies on model architecture, and propose a data-driven solution to mitigate the effect. On the one hand, we show that model architectures based on a dense Bird's Eye View (BEV) representation with backward projection, such as BEVFormer, are the most robust against varying sensor configurations. On the other hand, we propose a novel data-driven sensor adaptation pipeline based on neural rendering, which can transform entire datasets to match different camera sensor setups. Applying this approach improves performance across all investigated 3D object detectors, mitigating the cross-sensor domain gap by a large margin and reducing the need for new data collection by enabling efficient data reusability across vehicles with different sensor setups. The CamShift dataset and the sensor adaptation benchmark are available at https://dmholtz.github.io/camshift/.

The task of semantic instance segmentation has gained a large interest within academia as well as industry, especially in the context of autonomous driving. While several published approaches achieve very strong results, only few of them achieve frame rates that are sufficient for the automotive domain. We present an approach that achieves competitive results on the Cityscapes [1] and KITTI [2] datasets, while being twice as fast as any other existing approach. Our method relies on a single fully-convolutional network (FCN [3]) predicting object bounding boxes, as well as pixel-wise semantic object classes and an offset vector pointing to corresponding object centers. Using those outputs, we present an efficient and simple post-processing that assigns each object pixel to its best matching object detection, resulting in an instance segmentation obtained at real-time speeds.

In this paper, we consider convolutional neural networks operating on sparse inputs with an application to depth completion from sparse laser scan data. First, we show that traditional convolutional networks perform poorly when applied to sparse data even when the location of missing data is provided to the network. To overcome this problem, we propose a simple yet effective sparse convolution layer which explicitly considers the location of missing data during the convolution operation. We demonstrate the benefits of the proposed network architecture in synthetic and real experiments with respect to various baseline approaches. Compared to dense baselines, the proposed sparse convolution network generalizes well to novel datasets and is invariant to the level of sparsity in the data. For our evaluation, we derive a novel dataset from the KITTI benchmark, comprising over 94k depth annotated RGB images. Our dataset allows for training and evaluating depth completion and depth prediction techniques in challenging real-world settings and is available online at: www.cvlibs.net/datasets/kitti.

We state a combinatorial optimization problem whose feasible solutions define both a decomposition and a node labeling of a given graph. This problem offers a common mathematical abstraction of seemingly unrelated computer vision tasks, including instance-separating semantic segmentation, articulated human body pose estimation and multiple object tracking. Conceptually, it generalizes the unconstrained integer quadratic program and the minimum cost lifted multicut problem, both of which are NP-hard. In order to find feasible solutions efficiently, we define two local search algorithms that converge monotonously to a local optimum, offering a feasible solution at any time. To demonstrate the effectiveness of these algorithms in tackling computer vision tasks, we apply them to instances of the problem that we construct from published data, using published algorithms. We report state-of-the-art application-specific accuracy in the three above-mentioned applications.

In this paper we formulate structure from motion as a learning problem. We train a convolutional network end-to-end to compute depth and camera motion from successive, unconstrained image pairs. The architecture is composed of multiple stacked encoder-decoder networks, the core part being an iterative network that is able to improve its own predictions. The network estimates not only depth and motion, but additionally surface normals, optical flow between the images and confidence of the matching. A crucial component of the approach is a training loss based on spatial relative differences. Compared to traditional two-frame structure from motion methods, results are more accurate and more robust. In contrast to the popular depth-from-single-image networks, DeMoN learns the concept of matching and, thus, better generalizes to structures not seen during training.