Related papers: Visual Looming from Motion Field and Surface Norma…

Accurate 6-DoF object pose estimation and tracking are critical for reliable robotic manipulation. However, zero-shot methods often fail under viewpoint-induced ambiguities and fixed-camera setups struggle when objects move or become…

The visual simultaneous localization and mapping(vSLAM) is widely used in GPS-denied and open field environments for ground and surface robots. However, due to the frequent perception failures derived from lacking visual texture or the…

Vision language models (VLMs) have shown impressive capabilities across a variety of tasks, from logical reasoning to visual understanding. This opens the door to richer interaction with the world, for example robotic control. However, VLMs…

In this thesis we address two related aspects of visual object recognition: the use of motion information, and the use of internal supervision, to help unsupervised learning. These two aspects are inter-related in the current study, since…

Humans have a remarkable ability to predict the effect of physical interactions on the dynamics of objects. Endowing machines with this ability would allow important applications in areas like robotics and autonomous vehicles. In this work,…

Monocular vision-based navigation for automated driving is a challenging task due to the lack of enough information to compute temporal relationships among objects on the road. Optical flow is an option to obtain temporal information from…

Humans can easily deduce the relative pose of a previously unseen object, without labeling or training, given only a single query-reference image pair. This is arguably achieved by incorporating i) 3D/2.5D shape perception from a single…

Event cameras provide a natural and data efficient representation of visual information, motivating novel computational strategies towards extracting visual information. Inspired by the biological vision system, we propose a behavior driven…

We present a novel technique to estimate the 6D pose of objects from single images where the 3D geometry of the object is only given approximately and not as a precise 3D model. To achieve this, we employ a dense 2D-to-3D correspondence…

Object concepts play a foundational role in human visual cognition, enabling perception, memory, and interaction in the physical world. Inspired by findings in developmental neuroscience - where infants are shown to acquire object…

3D visual grounding (3DVG) identifies objects in 3D scenes from language descriptions. Existing zero-shot approaches leverage 2D vision-language models (VLMs) by converting 3D spatial information (SI) into forms amenable to VLM processing,…

We present a system for learning motion of independently moving objects from stereo videos. The only human annotation used in our system are 2D object bounding boxes which introduce the notion of objects to our system. Unlike prior learning…

In this work, we bridge the gap between recent pose estimation and tracking work to develop a powerful method for robots to track objects in their surroundings. Motion-Nets use a segmentation model to segment the scene, and separate…

This paper presents a new dual quaternion-based formulation for pose-based visual servoing. Extending our previous work on local contact moment (LoCoMo) based grasp planning, we demonstrate grasping of arbitrarily moving objects in 3D…

In this paper, we present a tightly-coupled visual-inertial object-level multi-instance dynamic SLAM system. Even in extremely dynamic scenes, it can robustly optimise for the camera pose, velocity, IMU biases and build a dense 3D…

Estimating motion from images is a well-studied problem in computer vision and robotics. Previous work has developed techniques to estimate the motion of a moving camera in a largely static environment (e.g., visual odometry) and to segment…

Recent approaches on visual scene understanding attempt to build a scene graph -- a computational representation of objects and their pairwise relationships. Such rich semantic representation is very appealing, yet difficult to obtain from…

Robust and accurate six degree-of-freedom tracking on portable devices remains a challenging problem, especially on small hand-held devices such as smartphones. For improved robustness and accuracy, complementary movement information from…

Mobile robots that navigate in unknown environments need to be constantly aware of the dynamic objects in their surroundings for mapping, localization, and planning. It is key to reason about moving objects in the current observation and at…

The basic idea behind evolutionary robotics is to evolve a set of neural controllers for a particular task at hand. It involves use of various input parameters such as infrared sensors, light sensors and vision based methods. This paper…