Related papers: Virtual Worlds as Proxy for Multi-Object Tracking …

Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…

World models learn to predict the temporal evolution of visual observations given a control signal, potentially enabling agents to reason about environments through forward simulation. Because of the focus on forward simulation, current…

While deep learning has been very successful in computer vision, real world operating conditions such as lighting variation, background clutter, or occlusion hinder its accuracy across several tasks. Prior work has shown that hybrid models…

For the last few decades, several major subfields of artificial intelligence including computer vision, graphics, and robotics have progressed largely independently from each other. Recently, however, the community has realized that…

We present a machine learning system that can quantify fine art paintings with a set of visual elements and principles of art. This formal analysis is fundamental for understanding art, but developing such a system is challenging. Paintings…

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the…

We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50,000+ 2D bounding boxes of object instances densely captured…

Visual tracking is a fundamental problem in computer vision. Recently, some deep-learning-based tracking algorithms have been achieving record-breaking performances. However, due to the high complexity of deep learning, most deep trackers…

Physical world knowledge resides mainly in videos. Equipping Vision-Language-Action (VLA) models with such knowledge is fundamental for safe and generalizable planning. Predictive world modeling enables VLA to internalize physical dynamics…

Standard 3D reconstruction pipelines assume stationary world, therefore suffer from `ghost artifacts' whenever dynamic objects are present in the scene. Recent approaches has started tackling this issue, however, they typically either only…

Visual navigation tasks in real-world environments often require both self-motion and place recognition feedback. While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end…

Models for long-term point tracking are typically trained on large synthetic datasets. The performance of these models degrades in real-world videos due to different characteristics and the absence of dense ground-truth annotations.…

In a real-world setting, visual recognition systems can be brought to make predictions for images belonging to previously unknown class labels. In order to make semantically meaningful predictions for such inputs, we propose a two-step…

Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples…

This paper tackles the problem of Cross-view Video-based camera Localization (CVL). The task is to localize a query camera by leveraging information from its past observations, i.e., a continuous sequence of images observed at previous time…

While stochastic video prediction models enable future prediction under uncertainty, they mostly fail to model the complex dynamics of real-world scenes. For example, they cannot provide reliable predictions for scenes with a moving camera…

Despite learning-based visual odometry (VO) has shown impressive results in recent years, the pretrained networks may easily collapse in unseen environments. The large domain gap between training and testing data makes them difficult to…

Real-time rendering of dynamic line sets is relevant in many visualization tasks, including unsteady flow visualization and interactive white matter reconstruction from Magnetic Resonance Imaging. High-quality global illumination and…

Tracking in urban street scenes plays a central role in autonomous systems such as self-driving cars. Most of the current vision-based tracking methods perform tracking in the image domain. Other approaches, eg based on LIDAR and radar,…

In recent years, the performance of object detection has advanced significantly with the evolving deep convolutional neural networks. However, the state-of-the-art object detection methods still rely on accurate bounding box annotations…