Image Generation

by Synced 2022-04-13 0

OpenAI’s unCLIP Text-to-Image System Leverages Contrastive and Diffusion Models to Achieve SOTA Performance

In the new paper Hierarchical Text-Conditional Image Generation with CLIP Latents, an OpenAI research team combines the advantages of contrastive and diffusion models for text-conditional image generation tasks. Their proposed unCLIP model improves image diversity with minimal loss in photorealism and caption similarity, and produces image quality comparable to the state-of-the-art text-to-image system GLIDE.

by Synced 2022-02-14 0

AI Computer Vision & Graphics Machine Learning & Data Science Research

Google’s MaskGIT Outperforms SOTA Transformer Models on Conditional Image Generation and Accelerates Autoregressive Decoding by up to 64x

A Google Research team proposes Masked Generative Image Transformer (MaskGIT), a novel image synthesis paradigm that uses a bidirectional transformer decoder. MaskGIT significantly outperforms state-of-the-art transformer models on the ImageNet dataset and accelerates autoregressive decoding by up to 64x.

by Synced 2020-09-22 3

Computer Vision & Graphics Popular

Tracking Recent Topics & Trends in 3D Photo Generation

Synced has identified a few significant technical advancements in the 3D photo field that we believe may be of interest to our readers.

by Synced 2020-08-04 4

AI Asia Computer Vision & Graphics Hot Machine Learning & Data Science Research

AI Generator Learns to ‘Draw’ Like Cartoonist Lee Mal-Nyeon in Just 10 Hours

A Seoul National University Master’s student and developer has trained a face generating model to transfer normal face photographs into cartoon images in the distinctive style of Lee Mal-nyeon.

by Synced 2020-06-18 11

Machine Learning & Data Science Nature Language Tech Research

From Texts to Kitties: OpenAI’s GPT Language Model Tackles Image Generation

Large transformer-based language models trained on pixel sequences can generate coherent images without the use of labels.

by Synced 2020-04-29 0

AI Computer Vision & Graphics Machine Learning & Data Science Research

Clova AI Releases StarGAN v2 Code, Pretrained Models and Datasets

South Korea’s Naver Clova AI Research is one of the institutions behind the unsupervised generative network U-GAT-IT. The tech hasContinue Reading

by Synced 2020-03-17 1

AI Research

‘Semantic Generation Pyramid’ for Image Generation and Manipulation

Researchers have proposed a new image generative model that leverages the hierarchical space of deep features learned by pretrained classification networks and provides a unified and versatile framework for image generation and manipulation tasks.

by Synced 2019-07-09 0

AI Research

BigGAN + BiGAN = BigBiGAN | DeepMind Model Excels in Unsupervised Representation Learning and Image Generation

Leading UK AI research company DeepMind has now proposed “BigBiGAN” (not BigBigGAN, but BigBiGAN), which achieves state-of-the-art results in both unsupervised representation learning on ImageNet and in unconditional image generation.

by Synced 2019-06-06 5

AI Research

Going Beyond GAN? New DeepMind VAE Model Generates High Fidelity Human Faces

Generative adversarial networks (GANs) have become AI researchers’ “go-to” technique for generating photo-realistic synthetic images. Now, DeepMind researchers say that there may be a better option.