Related papers: Orient Anything: Learning Robust Object Orientatio…
This paper presents a comprehensive pipeline for recognizing objects targeted by human pointing gestures using RGB images. As human-robot interaction moves toward more intuitive interfaces, the ability to identify targets of non-verbal…
Most model-free visual object tracking methods formulate the tracking task as object location estimation given by a 2D segmentation or a bounding box in each video frame. We argue that this representation is limited and instead propose to…
Object pose estimation is a crucial prerequisite for robots to perform autonomous manipulation in clutter. Real-world bin-picking settings such as warehouses present additional challenges, e.g., new objects are added constantly. Most of the…
Typical template-based object pose pipelines estimate the pose by retrieving the closest matching template and aligning it with the observed image. However, failure to retrieve the correct template often leads to inaccurate pose…
In the context of future manufacturing lines, removing fixtures will be a fundamental step to increase the flexibility of autonomous systems in assembly and logistic operations. Vision-based 3D pose estimation is a necessity to accurately…
We introduce a unified, end-to-end framework that seamlessly integrates object detection and pose estimation with a versatile onboarding process. Our pipeline begins with an onboarding stage that generates object representations from either…
While 3D object bounding box (bbox) representation has been widely used in autonomous driving perception, it lacks the ability to capture the precise details of an object's intrinsic geometry. Recently, occupancy has emerged as a promising…
Articulated objects are pervasive in daily life. However, due to the intrinsic high-DoF structure, the joint states of the articulated objects are hard to be estimated. To model articulated objects, two kinds of shape deformations namely…
Rotation-equivariance is an essential yet challenging property in oriented object detection. While general object detectors naturally leverage robustness to spatial shifts due to the translation-equivariance of the conventional CNNs,…
Gaze detection and head orientation are an important part of many advanced human-machine interaction applications. Many systems have been proposed for gaze detection. Typically, they require some form of user cooperation and calibration.…
6D object pose estimation is a prerequisite for many applications. In recent years, monocular pose estimation has attracted much research interest because it does not need depth measurements. In this work, we introduce ConvPoseCNN, a fully…
We present an algorithm to estimate the rotation pole of a principal-axis rotator using silhouette images collected from multiple camera poses. First, a set of images is stacked to form a single silhouette-stack image, where the object's…
Arbitrary-oriented object detection (AOOD) is a challenging task to detect objects in the wild with arbitrary orientations and cluttered arrangements. Existing approaches are mainly based on anchor-based boxes or dense points, which rely on…
We propose a complete pipeline that allows object detection and simultaneously estimate the pose of these multiple object instances using just a single image. A novel "keypoint regression" scheme with a cross-ratio term is introduced that…
Environment perception, including object detection and distance estimation, is one of the most crucial tasks for autonomous driving. Many attentions have been paid on the object detection task, but distance estimation only arouse few…
In this thesis we discuss architectural designs and training methods for a neural network to have the ability of dissecting an image into objects of interest without supervision. The main challenge in 2D unsupervised object segmentation is…
Real-time efficient perception is critical for autonomous navigation and city scale sensing. Orthogonal to architectural improvements, streaming perception approaches have exploited adaptive sampling improving real-time detection…
We propose an approach to predict the 3D shape and pose for the objects present in a scene. Existing learning based methods that pursue this goal make independent predictions per object, and do not leverage the relationships amongst them.…
Interpreting object-referential language and grounding objects in 3D with spatial relations and attributes is essential for robots operating alongside humans. However, this task is often challenging due to the diversity of scenes, large…
To act in the world, a model must name what it sees and know where it is in 3D. Today's vision-language models (VLMs) excel at open-ended 2D description and grounding, yet multi-object 3D detection remains largely missing from the VLM…