Related papers: LEAP: Liberate Sparse-view 3D Modeling from Camera…

We propose a CNN-based approach for multi-camera markerless motion capture of the human body. Unlike existing methods that first perform pose estimation on individual cameras and generate 3D models as post-processing, our approach makes use…

This work focuses on model-free zero-shot 6D object pose estimation for robotics applications. While existing methods can estimate the precise 6D pose of objects, they heavily rely on curated CAD models or reference images, the preparation…

Human-centric visual understanding is an important desideratum for effective human-robot interaction. In order to navigate crowded public places, social robots must be able to interpret the activity of the surrounding humans. This paper…

Recent advances in 3D Gaussian Splatting have shown promising results. Existing methods typically assume static scenes and/or multiple images with prior poses. Dynamics, sparse views, and unknown poses significantly increase the problem…

Camera relocalization involving a prior 3D reconstruction plays a crucial role in many mixed reality and robotics applications. Estimating the camera pose directly with respect to pre-built 3D models can be prohibitively expensive for…

The problem of identifying the 3D pose of a known object from a given 2D image has important applications in Computer Vision. Our proposed method of registering a 3D model of a known object on a given 2D photo of the object has numerous…

Existing 3D human pose estimation methods often suffer in performance, when applied to cross-scenario inference, due to domain shifts in characteristics such as camera viewpoint, position, posture, and body size. Among these factors, camera…

Recent methods for 6D pose estimation of objects assume either textured 3D models or real images that cover the entire range of target poses. However, it is difficult to obtain textured 3D models and annotate the poses of objects in real…

Neural Radiance Fields (NeRF) has demonstrated its superior capability to represent 3D geometry but require accurately precomputed camera poses during training. To mitigate this requirement, existing methods jointly optimize camera poses…

Human capabilities in understanding visual relations are far superior to those of AI systems, especially for previously unseen objects. For example, while AI systems struggle to determine whether two such objects are visually the same or…

Camera captured human pose is an outcome of several sources of variation. Performance of supervised 3D pose estimation approaches comes at the cost of dispensing with variations, such as shape and appearance, that may be useful for solving…

We consider the problem of relative pose regression in visual relocalization. Recently, several promising approaches have emerged in this area. We claim that even though they demonstrate on the same datasets using the same split to train…

Since the introduction of modern deep learning methods for object pose estimation, test accuracy and efficiency has increased significantly. For training, however, large amounts of annotated training data are required for good performance.…

With the recent advances in NeRF-based 3D aware GANs quality, projecting an image into the latent space of these 3D-aware GANs has a natural advantage over 2D GAN inversion: not only does it allow multi-view consistent editing of the…

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation,…

Estimating 3D poses of multiple humans in real-time is a classic but still challenging task in computer vision. Its major difficulty lies in the ambiguity in cross-view association of 2D poses and the huge state space when there are…

Despite the significant progress in six degrees-of-freedom (6DoF) object pose estimation, existing methods have limited applicability in real-world scenarios involving embodied agents and downstream 3D vision tasks. These limitations mainly…

Camera pose tracking attracts much interest both from academic and industrial communities, of which the methods based on planar markers are easy to be implemented. However, most of the existing methods need to identify multiple points in…

The increasing availability of video recordings made by multiple cameras has offered new means for mitigating occlusion and depth ambiguities in pose and motion reconstruction methods. Yet, multi-view algorithms strongly depend on camera…

We present Pose-NDF, a continuous model for plausible human poses based on neural distance fields (NDFs). Pose or motion priors are important for generating realistic new poses and for reconstructing accurate poses from noisy or partial…