Related papers: End-to-end Multi-Instance Robotic Reaching from Mo…

Visual servoing involves choosing actions that move a robot in response to observations from a camera, in order to reach a goal configuration in the world. Standard visual servoing approaches typically rely on manually designed features and…

Over many decades, researchers working in object recognition have longed for an end-to-end automated system that will simply accept 2D or 3D image or videos as inputs and output the labels of objects in the input data. Computer vision…

The general aim of multi-focus image fusion is to gather focused regions of different images to generate a unique all-in-focus fused image. Deep learning based methods become the mainstream of image fusion by virtue of its powerful feature…

Although numerous recent tracking approaches have made tremendous advances in the last decade, achieving high-performance visual tracking remains a challenge. In this paper, we propose an end-to-end network model to learn reinforced…

Convolutions on monocular dash cam videos capture spatial invariances in the image plane but do not explicitly reason about distances and depth. We propose a simple transformation of observations into a bird's eye view, also known as plan…

Vision-based interception using multicopters equipped strapdown camera is challenging due to camera-motion coupling and evasive targets. This paper proposes a method integrating Image-Based Visual Servoing (IBVS) with proportional…

We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the…

In this paper we propose an end-to-end learnable approach that detects static urban objects from multiple views, re-identifies instances, and finally assigns a geographic position per object. Our method relies on a Graph Neural Network…

We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system…

Most existing Multi-Object Tracking (MOT) approaches follow the Tracking-by-Detection paradigm and the data association framework where objects are firstly detected and then associated. Although deep-learning based method can noticeably…

The advances in deep reinforcement learning recently revived interest in data-driven learning based approaches to navigation. In this paper we propose to learn viewpoint invariant and target invariant visual servoing for local mobile robot…

We present an approach that learns to synthesize high-quality, novel views of 3D objects or scenes, while providing fine-grained and precise control over the 6-DOF viewpoint. The approach is self-supervised and only requires 2D images and…

Traditional visual place recognition (VPR) methods generally use frame-based cameras, which is easy to fail due to dramatic illumination changes or fast motions. In this paper, we propose an end-to-end visual place recognition network for…

The control of a robot for manipulation tasks generally relies on object detection and pose estimation. An attractive alternative is to learn control policies directly from raw input data. However, this approach is time-consuming and…

Autonomous scene exposure and exploration, especially in localization or communication-denied areas, useful for finding targets in unknown scenes, remains a challenging problem in computer navigation. In this work, we present a novel method…

Monocular depth estimation and ego-motion estimation are significant tasks for scene perception and navigation in stable, accurate and efficient robot-assisted endoscopy. To tackle lighting variations and sparse textures in endoscopic…

Instance segmentation has gained recently huge attention in various computer vision applications. It aims at providing different IDs to different object of the scene, even if they belong to the same class. This is useful in various…

We consider the task of semantic robotic grasping, in which a robot picks up an object of a user-specified class using only monocular images. Inspired by the two-stream hypothesis of visual reasoning, we present a semantic grasping…

Achieving robust vision-based humanoid locomotion remains challenging due to two fundamental issues: the sim-to-real gap introduces significant perception noise that degrades performance on fine-grained tasks, and training a unified policy…

While many visual ego-motion algorithm variants have been proposed in the past decade, learning based ego-motion estimation methods have seen an increasing attention because of its desirable properties of robustness to image noise and…