3D pose estimation | EPFL Graph Search

3D pose estimation is a process of predicting the transformation of an object from a user-defined reference pose, given an image or a 3D scan. It arises in computer vision or robotics where the pose or transformation of an object can be used for alignment of a computer-aided design models, identification, grasping, or manipulation of the object. The image data from which the pose of an object is determined can be either a single image, a stereo image pair, or an image sequence where, typically, the camera is moving with a known velocity. The objects which are considered can be rather general, including a living being or body parts, e.g., a head or hands. The methods which are used for determining the pose of an object, however, are usually specific for a class of objects and cannot generally be expected to work well for other types of objects. From an uncalibrated 2D camera It is possible to estimate the 3D rotation and translation of a 3D object from a single 2D photo,

Encoder-Decoder Models for Human Segmentation and Motion Analysis

Isinsu Katircioglu

Detecting people from 2D images and analyzing their motion in 3D have been long standing computer vision problems central to numerous applications such as autonomous driving and athletic training. Recently, with the availability of large amounts of training data and the advent of deep learning, the performance in human segmentation, 3D human pose prediction has improved significantly. However, these problems remain challenging due to several factors. In this thesis, we decompose the human motion analysis into three sub-tasks; 2D human segmentation, 3D human body pose estimation and 3D human motion forecasting. Our goal is to alleviate the challenges in these problems using various encoder-decoder models.

EPFL2022

Learning Robust Features and Latent Representations for Single View 3D Pose Estimation of Humans and Objects

Bugra Tekin

Estimating the 3D poses of rigid and articulated bodies is one of the fundamental problems of Computer Vision. It has a broad range of applications including augmented reality, surveillance, animation and human-computer interaction. Despite the ever-growing demand driven by the applications, predicting 3D pose from a 2D image is a challenging and ill-posed problem due to the loss of depth information during projection from 3D to 2D. Although there have been years of research on 3D pose estimation problem, it still remains unsolved. In this thesis, we propose a variety of ways to tackle the 3D pose estimation problem both for articulated human bodies and rigid object bodies by learning robust features and latent representations. First, we present a novel video-based approach that exploits spatiotemporal features for 3D human pose estimation in a discriminative regression scheme. While early approaches typically account for motion information by temporally regularizing noisy pose estimates in individual frames, we demonstrate that taking into account motion information very early in the modeling process with spatiotemporal features yields significant performance improvements. We further propose a CNN-based motion compensation approach that stabilizes and centralizes the human body in the bounding boxes of consecutive frames to increase the reliability of spatiotemporal features. This then allows us to effectively overcome ambiguities and improve pose estimation accuracy. Second, we develop a novel Deep Learning framework for structured prediction of 3D human pose. Our approach relies on an auto-encoder to learn a high-dimensional latent pose representation that accounts for joint dependencies. We combine traditional CNNs for supervised learning with auto-encoders for structured learning and demonstrate that our approach outperforms the existing ones both in terms of structure preservation and prediction accuracy. Third, we propose a 3D human pose estimation approach that relies on a two-stream neural network architecture to simultaneously exploit 2D joint location heatmaps and image features. We show that 2D pose of a person, predicted in terms of heatmaps by a fully convolutional network, provides valuable cues to disambiguate challenging poses and results in increased pose estimation accuracy. We further introduce a novel and generic trainable fusion scheme, which automatically learns where and how to fuse the features extracted from two different input modalities that a two-stream neural network operates on. Our trainable fusion framework selects the optimal network architecture on-the-fly and improves upon standard hard-coded network architectures. Fourth, we propose an efficient approach to estimate 3D pose of objects from a single RGB image. Existing methods typically detect 2D bounding boxes and then predict the object pose using a pipelined approach. The redundancy in different parts of the architecture makes such methods computationally expensive. Moreover, the final pose estimation accuracy depends on the accuracy of the intermediate 2D object detection step. In our method, the object is classified and its pose is regressed in a single shot from the full image using a single, compact fully convolutional neural network. Our approach achieves the state-of-the-art accuracy without requiring any costly pose refinement step and runs in real-time at 50 fps on a modern GPU, which is at least 5X faster than the state of the art.

EPFL2018

Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals

Pascal Fua, Semih Günel, Siyuan Li, Mirela Ostrek, Pavan P Ramdya, Helge Jochen Rhodin

Our goal is to capture the pose of neuroscience model organisms, without using any manual supervision, to be able to study how neural circuits orchestrate behaviour. Human pose estimation attains remarkable accuracy when trained on real or simulated datasets consisting of millions of frames. However, for many applications simulated models are unrealistic and real training datasets with comprehensive annotations do not exist. We address this problem with a new sim2real domain transfer method. Our key contribution is the explicit and independent modeling of appearance, shape and poses in an unpaired image translation framework. Our model lets us train a pose estimator on the target domain by transferring readily available body keypoint locations from the source domain to generated target images. We compare our approach with existing domain transfer methods and demonstrate improved pose estimation accuracy on Drosophila melanogaster (fruit fly), Caenorhabditis elegans (worm) and Danio rerio (zebrafish), without requiring any manual annotation on the target domain and despite using simplistic off-the-shelf animal characters for simulation, or simple geometric shapes as models. Our new datasets, code, and trained models will be published to support future neuroscientific studies.

2020

Learning Robust Features and Latent Representations for Single View 3D Pose Estimation of Humans and Objects

Bugra Tekin

EPFL2018