paper-with-me

Papers

SinIR: Efficient General Image Manipulation with Single Image Reconstruction

2021-06-14 · Jihyeong Yoo, Qifeng Chen

We propose SinIR, an efficient reconstruction-based framework trained on a single natural image for general image manipulation, including super-resolution, editing, harmonization, paint-to-image, photo-realistic style transfer, and artistic style transfer. We train our model on a single image with cascaded multi-scale learning, where each network at each scale is responsible for image reconstruction. This reconstruction objective greatly reduces the complexity and running time of training, compared to the GAN objective. However, the reconstruction objective also exacerbates the output quality. Therefore, to solve this problem, we further utilize simple random pixel shuffling, which also gives control over manipulation, inspired by the Denoising Autoencoder. With quantitative evaluation, we show that SinIR has competitive performance on various image manipulation tasks. Moreover, with a much simpler training objective (i.e., reconstruction), SinIR is trained 33.5 times faster than SinGAN (for 500 X 500 images) that solves similar tasks. Our code is publicly available at github.com/YooJiHyeong/SinIR.

📄 PDF Abstract BibTeX arXiv:2106.07140

Code (1)

YooJiHyeong/SinIR 공식 구현 pytorch

Tasks

DenoisingImage ManipulationImage ReconstructionStyle TransferSuper-Resolution

Methods 이 논문이 사용한 방법론

Denoising Autoencoder A Denoising Autoencoder is a modification on the autoencoder to prevent the network learning the identity function.…

Similar Papers 제목 키워드 기반

TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations

2021-12-16 · Shivangi Aneja, Lev Markhasin, Matthias Niessner

Face manipulation methods can be misused to affect an individual's privacy or to spread disinformation. To this end, we introduce a novel data-driven approach that produces image-specific perturbations which are embedded…

DeepFake DetectionDetecting Image ManipulationImage Manipulation

Image Shape Manipulation from a Single Augmented Training Sample

2020-07-02 · Yael Vinker, Eliahu Horwitz, Nir Zabari, Yedid Hoshen

In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of …

Image GenerationImage ManipulationImage-to-Image TranslationSketch-to-Image Translation

Image Shape Manipulation from a Single Augmented Training Sample

2021-09-13 · ICCV 2021 10 · Yael Vinker, Eliahu Horwitz, Nir Zabari, Yedid Hoshen

In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of …

Image GenerationImage ManipulationImage-to-Image TranslationSketch-to-Image Translation

LDEdit: Towards Generalized Text Guided Image Manipulation via Latent Diffusion Models

2022-10-05 · Paramanand Chandramouli, Kanchana Vaishnavi Gandikota

Research in vision-language models has seen rapid developments off-late, enabling natural language-based interfaces for image generation and manipulation. Many existing text guided manipulation techniques are restricted …

Image GenerationImage ManipulationStyle TransferText to Image Generation+1

Detecting Deepfakes with Self-Blended Images

2022-04-18 · CVPR 2022 1 · Kaede Shiohara, Toshihiko Yamasaki

In this paper, we present novel synthetic training data called self-blended images (SBIs) to detect deepfakes. SBIs are generated by blending pseudo source and target images from single pristine images, reproducing commo…

DeepFake Detection