paper-with-me

홈 › Papers

Latent-space disentanglement with untrained generator networks for the isolation of different motion types in video data

2022-05-20 · Abdullah Abdullah, Martin Holler, Karl Kunisch, Malena Sabate Landman

Isolating different types of motion in video data is a highly relevant problem in video analysis. Applications can be found, for example, in dynamic medical or biological imaging, where the analysis and further processing of the dynamics of interest is often complicated by additional, unwanted dynamics, such as motion of the measurement subject. In this work, it is empirically shown that a representation of video data via untrained generator networks, together with a specific technique for latent space disentanglement that uses minimal, one-dimensional information on some of the underlying dynamics, allows to efficiently isolate different, highly non-linear motion types. In particular, such a representation allows to freeze any selection of motion types, and to obtain accurate independent representations of other dynamics of interest. Obtaining such a representation does not require any pre-training on a training data set, i.e., all parameters of the generator network are learned directly from a single video.

📄 PDF Abstract BibTeX arXiv:2205.10367

Code (1)

hollerm/generator_based_motion_separation 공식 구현 pytorch

Tasks

DisentanglementImage Reconstruction

Similar Papers 제목 키워드 기반

Manifold Learning and Alignment with Generative Adversarial Networks

2019-09-25 · Jiseob Kim, Seungjae Jung, Hyundo Lee, Byoung-Tak Zhang

We present a generative adversarial network (GAN) that conducts manifold learning and alignment (MLA): A task to learn the multi-manifold structure underlying data and to align those manifolds without any correspondence …

DisentanglementGenerative Adversarial Network

FEAT: Face Editing with Attention

2022-02-06 · Xianxu Hou, Linlin Shen, Or Patashnik, Daniel Cohen-Or 외

Employing the latent space of pretrained generators has recently been shown to be an effective means for GAN-based face manipulation. The success of this approach heavily relies on the innate disentanglement of the laten…

Disentanglement

You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network

2020-06-30 · Boyun Li, Yuanbiao Gou, Shuhang Gu, Jerry Zitao Liu 외

In this paper, we study two challenging and less-touched problems in single image dehazing, namely, how to make deep learning achieve image dehazing without training on the ground-truth clean image (unsupervised) and a i…

DisentanglementImage DehazingSingle Image Dehazing

DPE: Disentanglement of Pose and Expression for General Video Portrait Editing

2023-01-16 · CVPR 2023 1 · Youxin Pang, Yong Zhang, Weize Quan, Yanbo Fan 외

One-shot video-driven talking face generation aims at producing a synthetic talking video by transferring the facial motion from a video to an arbitrary portrait image. Head pose and facial expression are always entangle…

DisentanglementFace GenerationTalking Face GenerationVideo Editing

The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement

2020-08-24 · ECCV 2020 8 · William Peebles, John Peebles, Jun-Yan Zhu, Alexei Efros 외

Existing disentanglement methods for deep generative models rely on hand-picked priors and complex encoder-based architectures. In this paper, we propose the Hessian Penalty, a simple regularization term that encourages …

Disentanglement