paper-with-me

홈 › Papers

Generative Visual Manipulation on the Natural Image Manifold

2016-09-12 · Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, Alexei A. Efros

Realistic image manipulation is challenging because it requires modifying the image appearance in a user-controlled way, while preserving the realism of the result. Unless the user has considerable artistic skill, it is easy to "fall off" the manifold of natural images while editing. In this paper, we propose to learn the natural image manifold directly from data using a generative adversarial neural network. We then define a class of image editing operations, and constrain their output to lie on that learned manifold at all times. The model automatically adjusts the output keeping all edits as realistic as possible. All our manipulations are expressed in terms of constrained optimization and are applied in near-real time. We evaluate our algorithm on the task of realistic photo manipulation of shape and color. The presented method can further be used for changing one image to look like the other, as well as generating novel imagery from scratch based on user's scribbles.

📄 PDF Abstract BibTeX arXiv:1609.03552

Code (1)

junyanz/iGAN 공식 구현 pytorch

Tasks

Image Manipulation

Similar Papers 제목 키워드 기반

GANalyze: Toward Visual Definitions of Cognitive Image Properties

2019-06-24 · ICCV 2019 10 · Authors, :, Lore Goetschalckx, Alex Andonian 외

We introduce a framework that uses Generative Adversarial Networks (GANs) to study cognitive properties like memorability, aesthetics, and emotional valence. These attributes are of interest because we do not have a conc…

Varying Manifolds in Diffusion: From Time-varying Geometries to Visual Saliency

2024-06-07 · JunHao Chen, Manyi Li, Zherong Pan, Xifeng Gao 외

Deep generative models learn the data distribution, which is concentrated on a low-dimensional manifold. The geometric analysis of distribution transformation provides a better understanding of data structure and enables…

Image Manipulation

Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold

2023-05-18 · Xingang Pan, Ayush Tewari, Thomas Leimkühler, Lingjie Liu 외

Synthesizing visual content that meets users' needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects. Existing approaches gain controllability of gen…

Image ManipulationPoint TrackingPosition

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation

2020-03-30 · ECCV 2020 8 · Xingang Pan, Xiaohang Zhan, Bo Dai, Dahua Lin 외

Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior th…

Generative Adversarial NetworkImage ManipulationImage MorphingImage Restoration

Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation

2020-10-23 · NeurIPS 2020 12 · Bowen Li, Xiaojuan Qi, Philip H. S. Torr, Thomas Lukasiewicz

We propose a novel lightweight generative adversarial network for efficient image manipulation using natural language descriptions. To achieve this, a new word-level discriminator is proposed, which provides the generato…

Generative Adversarial NetworkImage ManipulationText-to-Image Generation