BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike
Animated Motion
- URL: http://arxiv.org/abs/2306.16940v1
- Date: Thu, 29 Jun 2023 13:35:16 GMT
- Title: BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike
Animated Motion
- Authors: Michael J. Black, Priyanka Patel, Joachim Tesch, Jinlong Yang
- Abstract summary: We show that neural networks trained only on synthetic data achieve state-of-the-art accuracy on the problem of 3D human pose and shape estimation from real images.
Previous synthetic datasets have been small, unrealistic, or lacked realistic clothing.
- Score: 52.11972919802401
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We show, for the first time, that neural networks trained only on synthetic
data achieve state-of-the-art accuracy on the problem of 3D human pose and
shape (HPS) estimation from real images. Previous synthetic datasets have been
small, unrealistic, or lacked realistic clothing. Achieving sufficient realism
is non-trivial and we show how to do this for full bodies in motion.
Specifically, our BEDLAM dataset contains monocular RGB videos with
ground-truth 3D bodies in SMPL-X format. It includes a diversity of body
shapes, motions, skin tones, hair, and clothing. The clothing is realistically
simulated on the moving bodies using commercial clothing physics simulation. We
render varying numbers of people in realistic scenes with varied lighting and
camera motions. We then train various HPS regressors using BEDLAM and achieve
state-of-the-art accuracy on real-image benchmarks despite training with
synthetic data. We use BEDLAM to gain insights into what model design choices
are important for accuracy. With good synthetic training data, we find that a
basic method like HMR approaches the accuracy of the current SOTA method
(CLIFF). BEDLAM is useful for a variety of tasks and all images, ground truth
bodies, 3D clothing, support code, and more are available for research
purposes. Additionally, we provide detailed information about our synthetic
data generation pipeline, enabling others to generate their own datasets. See
the project page: https://bedlam.is.tue.mpg.de/.
Related papers
- VR-based generation of photorealistic synthetic data for training
hand-object tracking models [0.0]
"blender-hoisynth" is an interactive synthetic data generator based on the Blender software.
It is possible for users to interact with objects via virtual hands using standard Virtual Reality hardware.
We replace large parts of the training data in the well-known DexYCB dataset with hoisynth data and train a state-of-the-art HOI reconstruction model with it.
arXiv Detail & Related papers (2024-01-31T14:32:56Z) - Learning from synthetic data generated with GRADE [0.6982738885923204]
We present a framework for generating realistic animated dynamic environments (GRADE) for robotics research.
GRADE supports full simulation control, ROS integration, realistic physics, while being in an engine that produces high visual fidelity images and ground truth data.
We show that, even training using only synthetic data, can generalize well to real-world images in the same application domain.
arXiv Detail & Related papers (2023-05-07T14:13:04Z) - CIRCLE: Capture In Rich Contextual Environments [69.97976304918149]
We propose a novel motion acquisition system in which the actor perceives and operates in a highly contextual virtual world.
We present CIRCLE, a dataset containing 10 hours of full-body reaching motion from 5 subjects across nine scenes.
We use this dataset to train a model that generates human motion conditioned on scene information.
arXiv Detail & Related papers (2023-03-31T09:18:12Z) - PERGAMO: Personalized 3D Garments from Monocular Video [6.8338761008826445]
PERGAMO is a data-driven approach to learn a deformable model for 3D garments from monocular images.
We first introduce a novel method to reconstruct the 3D geometry of garments from a single image, and use it to build a dataset of clothing from monocular videos.
We show that our method is capable of producing garment animations that match the real-world behaviour, and generalizes to unseen body motions extracted from motion capture dataset.
arXiv Detail & Related papers (2022-10-26T21:15:54Z) - Capturing and Animation of Body and Clothing from Monocular Video [105.87228128022804]
We present SCARF, a hybrid model combining a mesh-based body with a neural radiance field.
integrating the mesh into the rendering enables us to optimize SCARF directly from monocular videos.
We demonstrate that SCARFs clothing with higher visual quality than existing methods, that the clothing deforms with changing body pose and body shape, and that clothing can be successfully transferred between avatars of different subjects.
arXiv Detail & Related papers (2022-10-04T19:34:05Z) - Playing for 3D Human Recovery [88.91567909861442]
In this work, we obtain massive human sequences by playing the video game with automatically annotated 3D ground truths.
Specifically, we contribute GTA-Human, a large-scale 3D human dataset generated with the GTA-V game engine.
A simple frame-based baseline trained on GTA-Human outperforms more sophisticated methods by a large margin.
arXiv Detail & Related papers (2021-10-14T17:49:42Z) - AGORA: Avatars in Geography Optimized for Regression Analysis [35.22486186509372]
AGORA is a synthetic dataset with high realism and highly accurate ground truth.
We create reference 3D poses and body shapes by fitting the SMPL-X body model (with face and hands) to the 3D scans.
We evaluate existing state-of-the-art methods for 3D human pose estimation on this dataset and find that most methods perform poorly on images of children.
arXiv Detail & Related papers (2021-04-29T20:33:25Z) - Neural 3D Clothes Retargeting from a Single Image [91.5030622330039]
We present a method of clothes; generating the potential poses and deformations of a given 3D clothing template model to fit onto a person in a single RGB image.
The problem is fundamentally ill-posed as attaining the ground truth data is impossible, i.e. images of people wearing the different 3D clothing template model model at exact same pose.
We propose a semi-supervised learning framework that validates the physical plausibility of 3D deformation by matching with the prescribed body-to-cloth contact points and clothing to fit onto the unlabeled silhouette.
arXiv Detail & Related papers (2021-01-29T20:50:34Z) - S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling [103.65625425020129]
We represent the pedestrian's shape, pose and skinning weights as neural implicit functions that are directly learned from data.
We demonstrate the effectiveness of our approach on various datasets and show that our reconstructions outperform existing state-of-the-art methods.
arXiv Detail & Related papers (2021-01-17T02:16:56Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.