HNHacker News
TopNewBestAskShowJobs

Hard_Space

5,646 karma · joined September 25, 2018

Freelance writer and editor, primarily on machine learning, artificial intelligence and big data. Former head of research content for Metaphysic.ai (now brahma.ai, an AI-focused section of DNEG).

https://martinanderson.ai

Email: martin@martinanderson.ai

submissionscomments

Better Human Facial Synthesis with Gaussian Splatting and Parametric Heads

blog.metaphysic.ai·2 pts·Hard_Space·
0

Deforming 3D Gaussian Splat Models with Cages, the Easy Way

blog.metaphysic.ai·1 pts·Hard_Space·
0

Editable Clothing Layers for Gaussian Splat Human Representations

blog.metaphysic.ai·1 pts·Hard_Space·
0

Harnessing Deep Metric Learning to Circumvent Video Streaming Encryption

arxiv.org·3 pts·Hard_Space·
0

The Challenge of Simulating Grain in Film Stocks of the Past

blog.metaphysic.ai·1 pts·Hard_Space·
0

Better Stable Diffusion Inpainting by Learning to Remove Real Objects

blog.metaphysic.ai·1 pts·Hard_Space·
0

Trying Out New Clothes in Stable Diffusion-Based Videos

blog.metaphysic.ai·1 pts·Hard_Space·
0

Repairing the Nightmarish Hands Produced by Stable Diffusion

blog.metaphysic.ai·1 pts·Hard_Space·
0

Improving Facial Expression Synthesis Through GAN-Based Frontalization

blog.metaphysic.ai·2 pts·Hard_Space·
0

Dealing with Unconventional Facial Expressions in Neural Synthesis

blog.metaphysic.ai·1 pts·Hard_Space·
0

High Resolution (and High Accuracy) Stable Diffusion with a Simple Hack

blog.metaphysic.ai·1 pts·Hard_Space·
0

Creating Lip-Synced Video from Audio Speech and Music

blog.metaphysic.ai·1 pts·Hard_Space·
0

Multitask Video Synthesis Without Fine-Tuning

blog.metaphysic.ai·1 pts·Hard_Space·
0

A Unified System for Facial Analysis

blog.metaphysic.ai·1 pts·Hard_Space·
0

The Continuing Struggle to Create Significant Motion in Text-to-Video Output

blog.metaphysic.ai·1 pts·Hard_Space·
0

Better Stable Diffusion Deepfakes with an Object-Oriented Programming Approach

blog.metaphysic.ai·1 pts·Hard_Space·
0

Will GPT-4 Run Doom?

arxiv.org·5 pts·Hard_Space·
2

Getting Real Transparency into Stable Diffusion

blog.metaphysic.ai·3 pts·Hard_Space·
0

Face-Swapping Directly in the Latent Space

blog.metaphysic.ai·2 pts·Hard_Space·
0

Plausible Stable Diffusion Video from a Single Image

blog.metaphysic.ai·2 pts·Hard_Space·
0

Better Neural Avatars from Just Five Face Images

blog.metaphysic.ai·2 pts·Hard_Space·
0

The Challenge of Preventing 'Identity Bleed' in Face Swaps

blog.metaphysic.ai·1 pts·Hard_Space·
0

Combating Stable Diffusion Face Forgery Through Frequency Analysis

blog.metaphysic.ai·2 pts·Hard_Space·
0

Multiple Cropping of Images May Improve AI Model Performance

blog.metaphysic.ai·1 pts·Hard_Space·
0

A Text-to-Video Method That Generates Some Action

blog.metaphysic.ai·4 pts·Hard_Space·
0

Reshaping the Human Body with CGI and Stable Diffusion

blog.metaphysic.ai·1 pts·Hard_Space·
0

An Old Algorithm May Be Holding Back New Generative AI Systems

blog.metaphysic.ai·3 pts·Hard_Space·
0

What's the Difference Between CGI and AI?

blog.metaphysic.ai·2 pts·Hard_Space·
0

Solving the 'Profile View' Crisis in Facial Image Synthesis

blog.metaphysic.ai·1 pts·Hard_Space·
0

Using Traditional CGI to Re-Sculpt Generative AI

blog.metaphysic.ai·2 pts·Hard_Space·
0
← PreviousPage 3 of 20Next →