Related papers: PhoCaL: A Multi-Modal Dataset for Category-Level O…
Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with…
Pose estimation commonly refers to computer vision methods that recognize people's body postures in images or videos. With recent advancements in deep learning, we now have compelling models to tackle the problem in real-time. Since these…
To address the challenge of short-term object pose tracking in dynamic environments with monocular RGB input, we introduce a large-scale synthetic dataset OmniPose6D, crafted to mirror the diversity of real-world conditions. We additionally…
We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly applied at test-time to a novel object without fine-tuning,…
Estimating the 6D object pose is an essential task in many applications. Due to the lack of depth information, existing RGB-based methods are sensitive to occlusion and illumination changes. How to extract and utilize the geometry features…
Fixation prediction (FP) in panoramic contents has been widely investigated along with the booming trend of virtual reality (VR) applications. However, another issue within the field of visual saliency, salient object detection (SOD), has…
6D object pose estimation, which predicts the transformation of an object relative to the camera, remains challenging for unseen objects. Existing approaches typically rely on explicitly constructing feature correspondences between the…
The problem of identifying the 3D pose of a known object from a given 2D image has important applications in Computer Vision ranging from robotic vision to image analysis. Our proposed method of registering a 3D model of a known object on a…
We propose a single-shot approach to determining 6-DoF pose of an object with available 3D computer-aided design (CAD) model from a single RGB image. Our method, dubbed MRC-Net, comprises two stages. The first performs pose classification…
Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant…
Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a single RGB camera. However, current methods rely on…
This work proposes a novel pose estimation model for object categories that can be effectively transferred to previously unseen environments. The deep convolutional network models (CNN) for pose estimation are typically trained and…
3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches…
This study addresses the challenge of accurate 6D pose estimation in Augmented Reality (AR), a critical component for seamlessly integrating virtual objects into real-world environments. Our research primarily addresses the difficulty of…
While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc.…
Geometric navigation is nowadays a well-established field of robotics and the research focus is shifting towards higher-level scene understanding, such as Semantic Mapping. When a robot needs to interact with its environment, it must be…
We propose and study open-vocabulary monocular 3D detection, a novel task that aims to detect objects of any categores in metric 3D space from a single RGB image. Existing 3D object detectors either rely on costly sensors such as LiDAR or…
Existing works on 2D pose estimation mainly focus on a certain category, e.g. human, animal, and vehicle. However, there are lots of application scenarios that require detecting the poses/keypoints of the unseen class of objects. In this…
3D hand-object pose estimation is an important issue to understand the interaction between human and environment. Current hand-object pose estimation methods require detailed 3D labels, which are expensive and labor-intensive. To tackle the…
Grasping user-specified objects is crucial for robotic assistants; however, most current 6-DoF grasp detection methods are object-agnostic, making it challenging to grasp specific targets from a scene. To achieve that, we present GoalGrasp,…