Related papers: Foveated Path Tracing with Configurable Sampling a…

Convolutional neural networks (CNNs) have demonstrated their superiority in numerous computer vision tasks, yet their computational cost results prohibitive for many real-time applications such as pedestrian detection which is usually…

Autonomous vehicles (AVs) rely on real-time perception systems to understand road environments and ensure safe navigation. However, implementing reliable perception algorithms on resource-constrained embedded platforms remains challenging…

Tracking any point based on image frames is constrained by frame rates, leading to instability in high-speed scenarios and limited generalization in real-world applications. To overcome these limitations, we propose an image-event fusion…

We introduce Synscapes -- a synthetic dataset for street scene parsing created using photorealistic rendering techniques, and show state-of-the-art results for training and validation as well as new types of analysis. We study the behavior…

Driving scene reconstruction and rendering have advanced significantly using the 3D Gaussian Splatting. However, most prior research has focused on the rendering quality along a pre-recorded vehicle path and struggles to generalize to…

Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales…

This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…

Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…

Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this…

Road detection or traversability analysis has been a key technique for a mobile robot to traverse complex off-road scenes. The problem has been mainly formulated in early works as a binary classification one, e.g. associating pixels with…

We estimate the radiance field of large-scale dynamic areas from multiple vehicle captures under varying environmental conditions. Previous works in this domain are either restricted to static environments, do not scale to more than a…

Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed by two seemingly opposed approaches: improving the realism…

Modern convolutional neural networks apply the same operations on every pixel in an image. However, not all image regions are equally important. To address this inefficiency, we propose a method to dynamically apply convolutions conditioned…

Previous studies have proposed image-based clutter measures that correlate with human search times and/or eye movements. However, most models do not take into account the fact that the effects of clutter interact with the foveated nature of…

Lines provide the significantly richer geometric structural information about the environment than points, so lines are widely used in recent Visual Odometry (VO) works. Since VO with lines use line tracking results to locate and map, line…

Ray tracing has become a standard for accurate radio propagation modeling, but suffers from exponential computational complexity, as the number of candidate paths scales with the number of objects raised to the interaction order. This…

Visual tracking is one of the most important application areas of computer vision. At present, most algorithms are mainly implemented on PCs, and it is difficult to ensure real-time performance when applied in the real scenario. In order to…

In this work, we present a dense tracking and mapping system named Vox-Fusion, which seamlessly fuses neural implicit representations with traditional volumetric fusion methods. Our approach is inspired by the recently developed implicit…

In this paper, we present a simple yet fast and robust algorithm which exploits the spatio-temporal context for visual tracking. Our approach formulates the spatio-temporal relationships between the object of interest and its local context…

Single visual object tracking from an unmanned aerial vehicle (UAV) poses fundamental challenges such as object occlusion, small-scale objects, background clutter, and abrupt camera motion. To tackle these difficulties, we propose to…