Stories by Hard_Space

Faking Depth Occlusion for Better Augmented Reality

Bringing Temporal Coherence to Stable Diffusion with Flow Maps

Nvidia Offers Real-Time Neural People Through a NeRF and GAN Pipeline

Achieving More Realistic Deepfakes by Making the Image ‘Worse’

Generating Temporally Coherent High Resolution Video with Stable Diffusion

Adobe’s DreamBooth Clone Is 100X Faster and Obtains Better Results

The Challenge of Using AI to Change Facial Expressions

JPEG Compressed Images Can Bypass Protections Against AI Editing

Coincidental Generation

VIVE3D: Meta’s GAN-Based Deepfake and Video-Altering Framework

The Small Faces That Vex AI Surveillance Systems

Carbon Emissions of Writing and Illustrating Are Lower for AI Than for Humans

GigaGAN: Stable Diffusion for Generative Adversarial Networks

Scaling Up GANs for Text-to-Image Synthesis [pdf]

Detecting Deepfakes by Studying ‘Disconnected’ Facial Expressions

Using the Internet as a ‘Live’ Dataset for AI Training

The Micro-Paper: Towards cheaper, citable research ideas and conversations [pdf]

Correcting ‘Selfie’-Based Facial Distortion

Obtaining Editable Neural Humans from Short Video Clips

ChatGPT: Jack of all trades, master of none

3 4 5 6 7 8 9 10 11 12