skip to main content

Title: Learning neural representation of camera pose with matrix representation of pose shift via view synthesis
How to effectively represent camera pose is an essential problem in 3D computer vision, especially in tasks such as camera pose regression and novel view synthesis. Traditionally, 3D position of the camera is represented by Cartesian coordinate and the orientation is represented by Euler angle or quaternions. These representations are manually designed, which may not be the most effective representation for downstream tasks. In this work, we propose an approach to learn neural representations of camera poses and 3D scenes, coupled with neural representations of local camera movements. Specifically, the camera pose and 3D scene are represented as vectors and the local camera movement is represented as a matrix operating on the vector of the camera pose. We demonstrate that the camera movement can further be parametrized by a matrix Lie algebra that underlies a rotation system in the neural space. The vector representations are then concatenated and generate the posed 2D image through a decoder network. The model is learned from only posed 2D images and corresponding camera poses, without access to depths or shapes. We conduct extensive experiments on synthetic and real datasets. The results show that compared with other camera pose representations, our learned representation is more robust to noise more » in novel view synthesis and more effective in camera pose regression. « less
Authors:
; ; ; ;
Award ID(s):
2015577
Publication Date:
NSF-PAR ID:
10289683
Journal Name:
IEEE Conference on Computer Vision and Pattern Recognition
ISSN:
2163-6648
Sponsoring Org:
National Science Foundation
More Like this
  1. We consider the task of 3D pose estimation and tracking of multiple people seen in an arbitrary number of camera feeds. We propose TesseTrack, a novel top-down approach that simultaneously reasons about multiple individuals’ 3D body joint reconstructions and associations in space and time in a single end-to-end learnable framework. At the core of our approach is a novel spatio-temporal formulation that operates in a common voxelized feature space aggregated from single- or multiple camera views. After a person detection step, a 4D CNN produces short-term persons pecific representations which are then linked across time by a differentiable matcher. Themore »linked descriptions are then merged and deconvolved into 3D poses. This joint spatio-temporal formulation contrasts with previous piecewise strategies that treat 2D pose estimation, 2D-to-3D lifting, and 3D pose tracking as independent sub-problems that are error-prone when solved in isolation. Furthermore, unlike previous methods, TesseTrack is robust to changes in the number of camera views and achieves very good results even if a single view is available at inference time. Quantitative evaluation of 3D pose reconstruction accuracy on standard benchmarks shows significant improvements over the state of the art. Evaluation of multi-person articulated 3D pose tracking in our novel evaluation framework demonstrates the superiority of TesseTrack over strong baselines.« less
  2. In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation. Our model directly takes 2D pose as input and learns a generalized 2D-3D mapping function. The proposed model consists of a base network which efficiently captures pose-aligned features and a hierarchy of Bi-directional RNNs (BRNN) on the top to explicitly incorporate a set of knowledge regarding human body configuration (i.e., kinematics, symmetry, motor coordination). The proposed model thus enforces high-level constraints over human poses. In learning, we develop a pose sample simulator to augment training samples in virtual camera views, which further improvesmore »our model generalizability. We validate our method on public 3D human pose benchmarks and propose a new evaluation protocol working on cross-view setting to verify the generalization capability of different methods.We empirically observe that most state-of-the-art methods encounter difficulty under such setting while our method can well handle such challenges.« less
  3. We propose UniPose+, a unified framework for 2D and 3D human pose estimation in images and videos. The UniPose+ architecture leverages multi-scale feature representations to increase the effectiveness of backbone feature extractors, with no significant increase in network size and no postprocessing. Current pose estimation methods heavily rely on statistical postprocessing or predefined anchor poses for joint localization. The UniPose+ framework incorporates contextual information across scales and joint localization with Gaussian heatmap modulation at the decoder output to estimate 2D and 3D human pose in a single stage with state-of-the-art accuracy, without relying on predefined anchor poses. The multi-scale representationsmore »allowed by the waterfall module in the UniPose+ framework leverage the efficiency of progressive filtering in the cascade architecture, while maintaining multi-scale fields-of-view comparable to spatial pyramid configurations. Our results on multiple datasets demonstrate that UniPose+, with a HRNet, ResNet or SENet backbone and waterfall module, is a robust and efficient architecture for single person 2D and 3D pose estimation in single images and videos.« less
  4. Existing approaches for learning word embedding often assume there are sufficient occurrences for each word in the corpus, such that the representation of words can be accurately estimated from their contexts. However, in real-world scenarios, out-of-vocabulary (a.k.a. OOV) words that do not appear in training corpus emerge frequently. How to learn accurate representations of these words to augment a pre-trained embedding by only a few observations is a challenging research problem. In this paper, we formulate the learning of OOV embedding as a few-shot regression problem by fitting a representation function to predict an oracle embedding vector (defined as embeddingmore »trained with abundant observations) based on limited contexts. Specifically, we propose a novel hierarchical attention network-based embedding framework to serve as the neural regression function, in which the context information of a word is encoded and aggregated from K observations. Furthermore, we propose to use Model-Agnostic Meta-Learning (MAML) for adapting the learned model to the new corpus fast and robustly. Experiments show that the proposed approach significantly outperforms existing methods in constructing an accurate embedding for OOV words and improves downstream tasks when the embedding is utilized.« less
  5. Existing methods for pedestrian motion trajectory prediction are learning and predicting the trajectories in the 2D image space. In this work, we observe that it is much more efficient to learn and predict pedestrian trajectories in the 3D space since the human motion occurs in the 3D physical world and and their behavior patterns are better represented in the 3D space. To this end, we use a stereo camera system to detect and track the human pose with deep neural networks. During pose estimation, these twin deep neural networks satisfy the stereo consistence constraint. We adapt the existing SocialGAN methodmore »to perform pedestrian motion trajectory prediction from the 2D to the 3D space. Our extensive experimental results demonstrate that our proposed method significantly improves the pedestrian trajectory prediction performance, outperforming existing state-of-the-art methods.« less