Related papers: Unsupervised 3D Keypoint Discovery with Multi-View…
Weakly supervised 3D object detection aims to learn a 3D detector with lower annotation cost, e.g., 2D labels. Unlike prior work which still relies on few accurate 3D annotations, we propose a framework to study how to leverage constraints…
The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this…
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…
Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly…
Existing marker-less motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, which narrows its application scenarios. Here we propose a fully automatic method that given multi-view video,…
We propose a method of estimating a 3D human pose from a single view without 3D supervision. The key to our method is to leverage the 2D diffusion priors of motion diffusion models (MDMs) pre-trained on large 2D human pose datasets.…
In this paper, we propose a new single shot method for multi-person 3D human pose estimation in complex images. The model jointly learns to locate the human joints in the image, to estimate their 3D coordinates and to group these…
3D patient body modeling is critical to the success of automated patient positioning for smart medical scanning and operating rooms. Existing CNN-based end-to-end patient modeling solutions typically require a) customized network designs…
Reliable markerless motion tracking of people participating in a complex group activity from multiple moving cameras is challenging due to frequent occlusions, strong viewpoint and appearance variations, and asynchronous video streams. To…
Unsupervised object modeling is important in robotics, especially for handling a large set of objects. We present a method for unsupervised 3D object discovery, reconstruction, and localization that exploits multiple instances of an…
Accurate 3D object detection in LiDAR point clouds is crucial for autonomous driving systems. To achieve state-of-the-art performance, the supervised training of detectors requires large amounts of human-annotated data, which is expensive…
Recovering 3D full-body human pose is a challenging problem with many applications. It has been successfully addressed by motion capture systems with body worn markers and multiple cameras. In this paper, we address the more challenging…
Accurate 3D human pose estimation (3D HPE) is crucial for enabling autonomous vehicles (AVs) to make informed decisions and respond proactively in critical road scenarios. Promising results of 3D HPE have been gained in several domains such…
Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various…
Estimating the 3D pose of a hand from a 2D image is a well-studied problem and a requirement for several real-life applications such as virtual reality, augmented reality, and hand gesture recognition. Currently, reasonable estimations can…
We present Multi-view Pose transformer (MvP) for estimating multi-person 3D poses from multi-view images. Instead of estimating 3D joint locations from costly volumetric representation or reconstructing the per-person 3D pose from multiple…
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…
This paper introduces a new algorithm for unsupervised learning of keypoint detectors and descriptors, which demonstrates fast convergence and good performance across different datasets. The training procedure uses homographic…
We study the problem of unsupervised physical object discovery. While existing frameworks aim to decompose scenes into 2D segments based off each object's appearance, we explore how physics, especially object interactions, facilitates…
Unsupervised object discovery aims to localize objects in images, while removing the dependence on annotations required by most deep learning-based methods. To address this problem, we propose a fully unsupervised, bottom-up approach, for…