Related papers: Human Performance Capture from Monocular Video in …

We present a novel framework to reconstruct complete 3D human shapes from a given target image by leveraging monocular unconstrained images. The objective of this work is to reproduce high-quality details in regions of the reconstructed…

We present PAD3R, a method for reconstructing deformable 3D objects from casually captured, unposed monocular videos. Unlike existing approaches, PAD3R handles long video sequences featuring substantial object deformation, large-scale…

We present a novel method for high detail-preserving human avatar creation from monocular video. A parameterized body model is refined and optimized to maximally resemble subjects from a video showing them from all sides. Our avatars…

This paper proposes a new method for live free-viewpoint human performance capture with dynamic details (e.g., cloth wrinkles) using a single RGBD camera. Our main contributions are: (i) a multi-layer representation of garments and body,…

Recent works on dynamic 3D neural field reconstruction assume the input from synchronized multi-view videos whose poses are known. The input constraints are often not satisfied in real-world setups, making the approach impractical. We show…

Training state-of-the-art models for human body pose and shape recovery from images or videos requires datasets with corresponding annotations that are really hard and expensive to obtain. Our goal in this paper is to study whether poses…

Recently, implicit neural representation has been widely used to generate animatable human avatars. However, the materials and geometry of those representations are coupled in the neural network and hard to edit, which hinders their…

We present Vid2Avatar-Pro, a method to create photorealistic and animatable 3D human avatars from monocular in-the-wild videos. Building a high-quality avatar that supports animation with diverse poses from a monocular video is challenging…

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…

Convolutional Neural Network based approaches for monocular 3D human pose estimation usually require a large amount of training images with 3D pose annotations. While it is feasible to provide 2D joint annotations for large corpora of…

We focus on the task of estimating a physically plausible articulated human motion from monocular video. Existing approaches that do not consider physics often produce temporally inconsistent output with motion artifacts, while…

Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structures from RGB inputs, due to its under-constrained nature.…

We propose a new model-based method to accurately reconstruct human performances captured outdoors in a multi-camera setup. Starting from a template of the actor model, we introduce a new unified implicit representation for both,…

Estimating human pose and shape from monocular images is a long-standing problem in computer vision. Since the release of statistical body models, 3D human mesh recovery has been drawing broader attention. With the same goal of obtaining…

We present XFormer, a novel human mesh and motion capture method that achieves real-time performance on consumer CPUs given only monocular images as input. The proposed network architecture contains two branches: a keypoint branch that…

The high frame rate is a critical requirement for capturing fast human motions. In this setting, existing markerless image-based methods are constrained by the lighting requirement, the high data bandwidth and the consequent high…

In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field of- view, etc. Direct estimation of 3D pose, body shape or motion on…

Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the…

Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets. However, this still leaves open the problem of capturing motions for which no such…

Appearance of dressed humans undergoes a complex geometric transformation induced not only by the static pose but also by its dynamics, i.e., there exists a number of cloth geometric configurations given a pose depending on the way it has…