相关论文: MonoLoco: Monocular 3D Pedestrian Localization and…

Inferring the 3D structure from a single image, particularly in occluded regions, remains a fundamental yet unsolved challenge in vision-centric autonomous driving. Existing unsupervised approaches typically train a neural radiance field…

Localizing objects in 3D space and understanding their associated 3D properties is challenging given only monocular RGB images. The situation is compounded by the loss of depth information during perspective projection. We present Center3D,…

Monocular 3D object detection continues to attract attention due to the cost benefits and wider availability of RGB cameras. Despite the recent advances and the ability to acquire data at scale, annotation cost and complexity still limit…

We present a learning-based model to infer the personalized 3D shape of people from a few frames (1-8) of a monocular video in which the person is moving, in less than 10 seconds with a reconstruction accuracy of 5mm. Our model learns to…

We propose UnLoc, an efficient data-driven solution for sequential camera localization within floorplans. Floorplan data is readily available, long-term persistent, and robust to changes in visual appearance. We address key limitations of…

Accurate distance estimation is a fundamental challenge in robotic perception, particularly in omnidirectional imaging, where traditional geometric methods struggle with lens distortions and environmental variability. In this work, we…

Monocular depth estimation plays a crucial role in 3D recognition and understanding. One key limitation of existing approaches lies in their lack of structural information exploitation, which leads to inaccurate spatial layout,…

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)…

In this paper, we present an approach for tracking people in monocular videos, by predicting their future 3D representations. To achieve this, we first lift people to 3D from a single frame in a robust way. This lifting includes information…

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose…

Human motion prediction, which plays a key role in computer vision, generally requires a past motion sequence as input. However, in real applications, a complete and correct past motion sequence can be too expensive to achieve. In this…

Pseudo-LiDAR-based methods for monocular 3D object detection have received considerable attention in the community due to the performance gains exhibited on the KITTI3D benchmark, in particular on the commonly reported validation split.…

3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution input, which however, is not always available in many…

Monocular 3D detection is a challenging task due to the lack of accurate 3D information. Existing approaches typically rely on geometry constraints and dense depth estimates to facilitate the learning, but often fail to fully exploit the…

We tackle the problem of Human Locomotion Forecasting, a task for jointly predicting the spatial positions of several keypoints on the human body in the near future under an egocentric setting. In contrast to the previous work that aims to…

Monocular depth prediction plays a crucial role in understanding 3D scene geometry. Although recent methods have achieved impressive progress in evaluation metrics such as the pixel-wise relative error, most methods neglect the geometric…

Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment. While significant progress has been achieved with expensive LiDAR point clouds, it poses a great challenge for…

3D human pose estimation from a monocular image or 2D joints is an ill-posed problem because of depth ambiguity and occluded joints. We argue that 3D human pose estimation from a monocular input is an inverse problem where multiple feasible…

We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task…

In 3D human pose estimation one of the biggest problems is the lack of large, diverse datasets. This is especially true for multi-person 3D pose estimation, where, to our knowledge, there are only machine generated annotations available for…