paper-with-me

Papers

Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance

2018-06-18 · ECCV 2018 9 · Zhixin Shu, Mihir Sahasrabudhe, Alp Guler, Dimitris Samaras, Nikos Paragios, Iasonas Kokkinos

In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deformation between a canonical coordinate system (template') and an observed image, while appearance is modeled in canonical', template, coordinates, thus discarding variability due to deformations. We introduce novel techniques that allow this approach to be deployed in the setting of autoencoders and show that this method can be used for unsupervised group-wise image alignment. We show experiments with expression morphing in humans, hands, and digits, face manipulation, such as shape and appearance interpolation, as well as unsupervised landmark localization. A more powerful form of unsupervised disentangling becomes possible in template coordinates, allowing us to successfully decompose face images into shading and albedo, and further manipulate face images.

📄 PDF Abstract BibTeX arXiv:1806.06503

Code (2)

stergioc/smooth-transformer tf
zhixinshu/DeformingAutoencoders-pytorch pytorch

Tasks

Unsupervised Facial Landmark Detection

Similar Papers 제목 키워드 기반

Unsupervised Part-Based Disentangling of Object Shape and Appearance

2019-03-16 · CVPR 2019 6 · Dominik Lorenz, Leonard Bereska, Timo Milbich, Björn Ommer

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to dise…

Appearance TransferImage GenerationObjectPose Prediction+3

Unsupervised Part Segmentation through Disentangling Appearance and Shape

2021-05-26 · CVPR 2021 1 · Shilong Liu, Lei Zhang, Xiao Yang, Hang Su 외

We study the problem of unsupervised discovery and segmentation of object parts, which, as an intermediate local representation, are capable of finding intrinsic object structure and providing more explainable recognitio…

DisentanglementObjectSegmentationSemantic Segmentation+1

EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos

2023-07-21 · Ruyi Zha, Xuelian Cheng, Hongdong Li, Mehrtash Harandi 외

Reconstructing soft tissues from stereo endoscope videos is an essential prerequisite for many medical applications. Previous methods struggle to produce high-quality geometry and appearance due to their inadequate repre…

Surface Reconstruction

Transfer Learning using Spectral Convolutional Autoencoders on Semi-Regular Surface Meshes

2022-12-12 · Sara Hahner, Felix Kerkhoff, Jochen Garcke

The underlying dynamics and patterns of 3D surface meshes deforming over time can be discovered by unsupervised learning, especially autoencoders, which calculate low-dimensional embeddings of the surfaces. To study the …

Transfer Learning

Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose

2020-03-29 · Xianfang Zeng, Yusu Pan, Mengmeng Wang, Jiangning Zhang 외

Recent works have shown how realistic talking face images can be obtained under the supervision of geometry guidance, e.g., facial landmark or boundary. To alleviate the demand for manual annotations, in this paper, we p…

Face Reenactment