Related papers: AnyImageNav: Any-View Geometry for Precise Last-Me…
Recent progress in zero-shot 6D object pose estimation has been driven largely by large-scale models and cloud-based inference. However, these approaches often introduce high latency, elevated energy consumption, and deployment risks…
Deep learning has shown to be effective for robust and real-time monocular image relocalisation. In particular, PoseNet is a deep convolutional neural network which learns to regress the 6-DOF camera pose from a single image. It learns to…
We introduce Any6D, a model-free framework for 6D object pose estimation that requires only a single RGB-D anchor image to estimate both the 6D pose and size of unknown objects in novel scenes. Unlike existing methods that rely on textured…
Multi-camera 3D object detection for autonomous driving is a challenging problem that has garnered notable attention from both academia and industry. An obstacle encountered in vision-based techniques involves the precise extraction of…
We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs, with or without known camera poses. In pursuit of minimal modeling, DA3 yields two key insights: a single…
Recent image-goal navigation (ImageNav) methods learn a perception-action policy by separately capturing semantic features of the goal and egocentric images, then passing them to a policy network. However, challenges remain: (1) Semantic…
In this work, we introduce a novel method for calculating the 6DoF pose of an object using a single RGB-D image. Unlike existing methods that either directly predict objects' poses or rely on sparse keypoints for pose recovery, our approach…
Detecting objects and their 6D poses from only RGB images is an important task for many robotic applications. While deep learning methods have made significant progress in visual object detection and segmentation, the object pose estimation…
In this paper, we propose a novel network framework for indoor 3D object detection to handle variable input frame numbers in practical scenarios. Existing methods only consider fixed frames of input data for a single detector, such as…
Camera localization is a fundamental and key component of autonomous driving vehicles and mobile robots to localize themselves globally for further environment perception, path planning and motion control. Recently end-to-end approaches…
Image goal navigation requires two different skills: firstly, core navigation skills, including the detection of free space and obstacles, and taking decisions based on an internal representation; and secondly, computing directional…
Optical cameras are gaining popularity as the suitable sensor for relative navigation in space due to their attractive sizing, power and cost properties when compared to conventional flight hardware or costly laser-based systems. However, a…
In this paper, we investigate visual-based camera re-localization with neural networks for robotics and autonomous vehicles applications. Our solution is a CNN-based algorithm which predicts camera pose (3D translation and 3D rotation)…
Can an autonomous agent navigate in a new environment without building an explicit map? For the task of PointGoal navigation ('Go to $\Delta x$, $\Delta y$') under idealized settings (no RGB-D and actuation noise, perfect GPS+Compass), the…
PointGoal navigation in indoor environment is a fundamental task for personal robots to navigate to a specified point. Recent studies solved this PointGoal navigation task with near-perfect success rate in photo-realistically simulated…
Zero-Shot Object Goal Navigation (ZS-OGN) enables robots or agents to navigate toward objects of unseen categories without object-specific training. Traditional approaches often leverage categorical semantic information for navigation…
We present GigaPose, a fast, robust, and accurate method for CAD-based novel object pose estimation in RGB images. GigaPose first leverages discriminative "templates", rendered images of the CAD models, to recover the out-of-plane rotation…
Maps are a key component in image-based camera localization and visual SLAM systems: they are used to establish geometric constraints between images, correct drift in relative pose estimation, and relocalize cameras after lost tracking. The…
This paper studies the complex task of simultaneous multi-object 3D reconstruction, 6D pose and size estimation from a single-view RGB-D observation. In contrast to instance-level pose estimation, we focus on a more challenging problem…
Image-goal navigation is a challenging task that requires an agent to navigate to a goal indicated by an image in unfamiliar environments. Existing methods utilizing diverse scene memories suffer from inefficient exploration since they use…