Related papers: Physically Guided Visual Mass Estimation from a Si…

Inertial mass plays a crucial role in robotic applications such as object grasping, manipulation, and simulation, providing a strong prior for planning and control. Accurately estimating an object's mass before interaction can significantly…

Robotic manipulation requires accurate perception of the environment, which poses a significant challenge due to its inherent complexity and constantly changing nature. In this context, RGB image and point-cloud observations are two…

Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D…

Vision-Language Models (VLMs) are increasingly applied to robotic perception and manipulation, yet their ability to infer physical properties required for manipulation remains limited. In particular, estimating the mass of real-world…

Predicting 3D shapes and poses of static objects from a single RGB image is an important research area in modern computer vision. Its applications range from augmented reality to robotics and digital content creation. Typically this task is…

Accurate volume estimation of objects from visual data is a long-standing challenge in computer vision with significant applications in robotics, logistics, and smart health. Existing methods often rely on complex 3D reconstruction…

Monocular 3D object detection is of great significance for autonomous driving but remains challenging. The core challenge is to predict the distance of objects in the absence of explicit depth information. Unlike regressing the distance as…

In this paper, we present a novel generalizable object pose estimation method to determine the object pose using only one RGB image. Unlike traditional approaches that rely on instance-level object pose estimation and necessitate extensive…

Deep learning techniques have enabled rapid progress in monocular depth estimation, but their quality is limited by the ill-posed nature of the problem and the scarcity of high quality datasets. We estimate depth from a single camera by…

Monocular depth estimation is often described as an ill-posed and inherently ambiguous problem. Estimating depth from 2D images is a crucial step in scene reconstruction, 3Dobject recognition, segmentation, and detection. The problem can be…

Monocular depth estimation can play an important role in addressing the issue of deriving scene geometry from 2D images. It has been used in a variety of industries, including robots, self-driving cars, scene comprehension, 3D…

Understanding the shape of a scene from a single color image is a formidable computer vision task. However, most methods aim to predict the geometry of surfaces that are visible to the camera, which is of limited use when planning paths for…

The 3D localisation of an object and the estimation of its properties, such as shape and dimensions, are challenging under varying degrees of transparency and lighting conditions. In this paper, we propose a method for jointly localising…

Augmenting RGB data with measured depth has been shown to improve the performance of a range of tasks in computer vision including object detection and semantic segmentation. Although depth sensors such as the Microsoft Kinect have…

Estimating metric relative camera pose from a pair of images is of great importance for 3D reconstruction and localisation. However, conventional two-view pose estimation methods are not metric, with camera translation known only up to a…

Recently there has been a growing interest in category-level object pose and size estimation, and prevailing methods commonly rely on single view RGB-D images. However, one disadvantage of such methods is that they require accurate depth…

We propose a method to detect and reconstruct multiple 3D objects from a single RGB image. The key idea is to optimize for detection, alignment and shape jointly over all objects in the RGB image, while focusing on realistic and physically…

Current monocular-based 6D object pose estimation methods generally achieve less competitive results than RGBD-based methods, mostly due to the lack of 3D information. To make up this gap, this paper proposes a 3D geometric volume based…

Existing inverse physics methods recover physical parameters from multi-view videos, where geometric constraints across views resolve scale and 3D structure. In monocular settings, however, such constraints are absent, leading to severe…

Dietary assessment is a key contributor to monitoring health status. Existing self-report methods are tedious and time-consuming with substantial biases and errors. Image-based food portion estimation aims to estimate food energy values…