paper-with-me

Papers

Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion

2019-04-26 · Mihir Sahasrabudhe, Zhixin Shu, Edward Bartrum, Riza Alp Guler, Dimitris Samaras, Iasonas Kokkinos

In this work we introduce Lifting Autoencoders, a generative 3D surface-based model of object categories. We bring together ideas from non-rigid structure from motion, image formation, and morphable models to learn a controllable, geometric model of 3D categories in an entirely unsupervised manner from an unstructured set of images. We exploit the 3D geometric nature of our model and use normal information to disentangle appearance into illumination, shading and albedo. We further use weak supervision to disentangle the non-rigid shape variability of human faces into identity and expression. We combine the 3D representation with a differentiable renderer to generate RGB images and append an adversarially trained refinement network to obtain sharp, photorealistic image reconstruction results. The learned generative model can be controlled in terms of interpretable geometry and appearance factors, allowing us to perform photorealistic image manipulation of identity, expression, 3D pose, and illumination properties.

📄 PDF Abstract BibTeX arXiv:1904.11960

Code (0)

등록된 구현이 없습니다.

Tasks

Image ManipulationImage Reconstruction

Similar Papers 제목 키워드 기반

MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation

2021-11-01 · Safa C. Medin, Bernhard Egger, Anoop Cherian, Ye Wang 외

Recent advances in generative adversarial networks (GANs) have led to remarkable achievements in face image synthesis. While methods that use style-based GANs can generate strikingly photorealistic face images, it is oft…

DisentanglementImage GenerationImage Manipulation

Unsupervised Model Selection for Variational Disentangled Representation Learning

2019-05-29 · ICLR 2020 1 · Sunny Duan, Loic Matthey, Andre Saraiva, Nicholas Watters 외

Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning tasks. To extend the benefits of disentangled representations …

AttributeDisentanglementFairnessmodel+3

i3DMM: Deep Implicit 3D Morphable Model of Human Heads

2020-11-28 · CVPR 2021 1 · Tarun Yenamandra, Ayush Tewari, Florian Bernard, Hans-Peter Seidel 외

We present the first deep implicit 3D morphable model (i3DMM) of full heads. Unlike earlier morphable face models it not only captures identity-specific geometry, texture, and expressions of the frontal face, but also mo…

Evaluating unsupervised disentangled representation learning for genomic discovery and disease risk prediction

2023-07-17 · Taedong Yun

High-dimensional clinical data have become invaluable resources for genetic studies, due to their accessibility in biobank-scale datasets and the development of high performance modeling techniques especially using deep …

Representation Learning

Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions

2021-08-14 · Andrea Burns, Aaron Sarna, Dilip Krishnan, Aaron Maschinot

Disentangled visual representations have largely been studied with generative models such as Variational AutoEncoders (VAEs). While prior work has focused on generative methods for disentangled representation learning, t…

Contrastive LearningDisentanglementRepresentation LearningSensitivity