Research & Announcements
Incorporating ML Research Into Audio Production: ExFlowSions Case Study
SEED
Jun 25, 2024
Mónica Villanueva and Jorge García present the challenges and lessons learned from turning a machine learning generative model from a research project into a game production tool.
Beyond White Noise for Real-Time Rendering
SEED
May 14, 2024
SEED’s Alan Wolfe discusses the use of different types of noise for random number generation, focusing on the application of blue noise in rendering images for gaming.
Evaluating Gesture Generation in a Large-Scale Open Challenge
SEED
May 9, 2024
This paper, published in Transactions on Graphics, reports on the second GENEA Challenge, a project to benchmark data-driven automatic co-speech gesture generation.
Filter-Adapted Spatio-Temporal Sampling for Real-Time Rendering
SEED
May 1, 2024
This paper, presented at I3D 2024, discusses how to tailor the frequencies of rendering noise to improve image denoising in real time rendering.
From Photo to Expression: Generating Photorealistic Facial Rigs
SEED
Apr 25, 2024
This presentation from GDC 2024 discusses how machine learning can improve facial animation.
EA presents on graphics, gameplay, and generative tech at GDC 2024
Electronic Arts Inc., SEED, Frostbite
Mar 12, 2024
Don’t miss these GDC 2024 talks from Electronic Arts engineers, scientists, and technical artists.
SEED’s Voice2Face Honored by Fast Company
SEED
Dec 5, 2023
Electronic Arts and SEED’s Voice2Face project have been named one of Fast Company’s Next Big Things in Tech!
Coverage Bitmasks for Efficient Rendering Algorithms
SEED
Nov 29, 2023
This presentation gives the humble old bitmask the attention it deserves. It discusses where they have been used creatively and where they can be used.
GENEA Challenge 2023: Evaluating Gesture Generation with Two Speakers
SEED
Oct 10, 2023
This paper reports on the third GENEA Challenge, which benchmarks data-driven automatic co-speech gesture generation.
SEED Applies ML Research to the Growing Demands of AAA Game Testing
SEED
Aug 29, 2023
This year at the IEEE Conference on Games (CoG), SEED researchers presented five papers and a keynote presentation that explored the potential for imitation learning, reinforcement learning, and AI to significantly improve current game testing methods.
CoG 2023: Generating Personas for Games with Multimodal Adversarial Imitati…
SEED
Aug 16, 2023
This paper presents a novel imitation learning approach to generate multiple persona policies for playtesting: Multimodal Generative Adversarial Imitation Learning.
CoG 2023: Efficient Ground Vehicle Path Following in Game AI
SEED
Aug 14, 2023
This short paper presents an efficient path-following solution for ground vehicles tailored to game AI.
CoG 2023: Technical Challenges of Deploying Reinforcement Learning Agents f…
SEED
Jul 26, 2023
This paper describes an effort to add an experimental reinforcement learning system to an existing automated game-testing solution based on scripted bots in order to increase its capacity.
A Comprehensive Review of Data-Driven Co-Speech Gesture Generation
SEED
May 8, 2023
This review article summarizes co-speech gesture generation research, with a particular focus on deep generative models.
Siggraph Asia 2022: Rig Inversion by Training a Differentiable Rig Function
SEED
Dec 5, 2022
This paper proposed a differentiable function to solve rig inversion; a mathematical approach that allows animators to remap an existing mesh animation onto an animation rig.
Imitation Learning to Inform the Design of Computer Games
SEED
Nov 24, 2022
This paper proposes a new approach to automated game validation and testing that uses an imitation learning technique that requires and no specialist knowledge of machine learning or programming.
GENEA Challenge 2022: Co-Speech Gesture Generation
SEED
Nov 4, 2022
This paper reports on the second GENEA Challenge, which benchmarks data-driven automatic co-speech gesture generation.
AIIDE22: Synthesis of Sound Effects Using Generative Models
SEED
Oct 24, 2022
Research paper from AIIDE22: Generating controllable variations of sound effects that can be used in the creative process of sound designers.
Blogs
Machine Learning for Game Devs: Part 3
SEED
Jan 16, 2024
An introduction to machine learning for game developers using C++. Part 3: Training a neural network.
Machine Learning for Game Devs: Part 2
SEED
Nov 16, 2023
A developer-friendly introduction to machine learning using C++. Part 2 of 3: How do you figure out a neural network’s optimal weight and bias values
Machine Learning for Game Devs: Part 1
SEED
Oct 26, 2023
A developer-friendly introduction to machine learning using C++. Part 1 of 3: Understanding and working with a “classic” neural network.
Constant Time Stateless Shuffling and Grouping
SEED
Sep 6, 2023
Stateless shuffling is a technique for shuffling items and arranging them into groups of specific sizes — without actually shuffling or grouping anything.
Video: Some of SEED’s Greatest Hits
SEED
Jun 21, 2022
A teaser of some of our past and upcoming published research.
AI in Game Industry: Building New Worlds and New Mindsets
SEED
Jan 10, 2022
AI in Game Industry: Building New Worlds and New Mindsets
SEED at IEEE CoG 2021
SEED
Aug 24, 2021
SEED’s team presented two papers at this year’s 3rd IEEE Conference on Games.
SEED at SIGGRAPH 2021
SEED
Aug 10, 2021
SEED is well-represented at SIGGRAPH 2021. We have three presentations from developers at SEED showcasing some of our most exciting recent work.
SEED at SIGGRAPH 2019
SEED
Jul 22, 2019
SEED at SIGGRAPH 2019
SEED at GDC & GTC 2018
SEED
Jul 25, 2018
SEED at GDC & GTC 2018