Related papers: Optical Flow augmented Semantic Segmentation netwo…
Standard frame-based cameras that sample light intensity frames are heavily impacted by motion blur for high-speed motion and fail to perceive scene accurately when the dynamic range is high. Event-based cameras, on the other hand, overcome…
Deep neural object detection or segmentation networks are commonly trained with pristine, uncompressed data. However, in practical applications the input images are usually deteriorated by compression that is applied to efficiently transmit…
Critical research about camera-and-LiDAR-based semantic object segmentation for autonomous driving significantly benefited from the recent development of deep learning. Specifically, the vision transformer is the novel ground-breaker that…
Real-time moving object detection in unconstrained scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource. In this paper, an optical flow based moving object detection…
Optical flow estimation is crucial for various applications in vision and robotics. As the difficulty of collecting ground truth optical flow in real-world scenarios, most of the existing methods of learning optical flow still adopt…
The performance of optical flow algorithms greatly depends on the specifics of the content and the application for which it is used. Existing and well established optical flow datasets are limited to rather particular contents from which…
LiDAR scene flow is the task of estimating per-point 3D motion between consecutive point clouds. Recent methods achieve centimeter-level accuracy on popular autonomous vehicle (AV) datasets, but are typically only trained and evaluated on a…
Recent visual odometry (VO) methods incorporating geometric algorithm into deep-learning architecture have shown outstanding performance on the challenging monocular VO task. Despite encouraging results are shown, previous methods ignore…
Event-based cameras can overpass frame-based cameras limitations for important tasks such as high-speed motion detection during self-driving cars navigation in low illumination conditions. The event cameras' high temporal resolution and…
Although multi-scale concepts have recently proven useful for recurrent network architectures in the field of optical flow and stereo, they have not been considered for image-based scene flow so far. Hence, based on a single-scale recurrent…
Estimating per-pixel motion between video frames, known as optical flow, is a long-standing problem in video understanding and analysis. Most contemporary optical flow techniques largely focus on addressing the cross-image matching with…
Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the existing optical…
In this paper, we focus on exploring effective methods for faster and accurate semantic segmentation. A common practice to improve the performance is to attain high-resolution feature maps with strong semantic representation. Two strategies…
Recent works on optical flow estimation use neural networks to predict the flow field that maps positions of one image to positions of the other. These networks consist of a feature extractor, a correlation volume, and finally several…
Autonomous vehicles are the next revolution in the automobile industry and they are expected to revolutionize the future of transportation. Understanding the scenario in which the autonomous vehicle will operate is critical for its…
Estimating 3D occupancy and motion at the vehicle's surroundings is essential for autonomous driving, enabling situational awareness in dynamic environments. Existing approaches jointly learn geometry and motion but rely on expensive 3D…
Real-time high-accuracy optical flow estimation is critical for a variety of real-world robotic applications. However, current learning-based methods often struggle to balance accuracy and computational efficiency: methods that achieve high…
Accurate velocity estimation is critical in mobile robotics, particularly for driver assistance systems and autonomous driving. Wheel odometry fused with Inertial Measurement Unit (IMU) data is a widely used method for velocity estimation;…
This paper describes a fully spike-based neural network for optical flow estimation from Dynamic Vision Sensor data. A low power embedded implementation of the method which combines the Asynchronous Time-based Image Sensor with IBM's…
Semantic scene understanding is important for various applications. In particular, self-driving cars need a fine-grained understanding of the surfaces and objects in their vicinity. Light detection and ranging (LiDAR) provides precise…