AI4Animation

Features

Motion Synthesis Models - Provides a deep learning system to generate biped and quadruped locomotion from motion capture data.
Neural Model Training - Provides a deep learning system for training neural networks that control the movement and behavior of biped and quadruped characters.
Locomotion Training - Provides a framework for training neural networks to generate biped and quadruped locomotion from motion capture data.
Neural Animation Drivers - Executes trained deep learning models within a game engine to generate character joint rotations based on real-time inputs.
Video and Motion Synthesis - Trains deep learning models to generate biped and quadruped locomotion from raw motion capture data.
Character Animation Runtimes - Executes trained neural networks within a game engine to drive real-time character animations based on inputs.
Inverse Kinematics Character Animations - Implements a real-time system to compute joint positions for characters to reach target goals using inverse kinematics.
Neural Animation Runtimes - Provides a framework for executing trained neural networks to drive real-time character motion within Unity.
Data Processing Pipelines - Implements a pipeline for importing and cleaning animation data from FBX and BVH formats for neural network training.
Manifold-Based Motion Extraction - Learns periodic features and spatial-temporal structures from datasets to improve alignment and similarity measures for motion capture.
Motion Phase Manifold Extraction - Learns periodic features and spatial-temporal structures from motion datasets to improve alignment and similarity measures.
Inverse Kinematics - Provides a real-time solver for computing joint configurations to reach specific target goals.
Environment-Adaptive Animations - Generates character movements that adapt to scene geometry for actions like sitting or obstacle avoidance.
Neural Animation Blending - Synthesizes novel movement combinations by imitating animation layering to mix and blend unaligned motion sources.
Motion Retargeting - Translates sparse sensor signals into full-body avatar motions in real-time while preserving original motion context.
Imitative Layering - Synthesizes novel movement combinations by blending unaligned motion sources to simulate traditional animation layer mixing.
Neural Blending Systems - Synthesizes novel movements by mixing unaligned motion sources using learned manifolds.

Open-source alternatives to AI4Animation

Similar open-source projects, ranked by how many features they share with AI4Animation.

esotericsoftware/spine-runtimes
EsotericSoftware/spine-runtimes
4,997View on GitHub
Spine Runtimes is a 2D skeletal animation runtime library that loads and plays back animations created with the Spine design tool. It manages a skeleton hierarchy of bones, slots, and attachments, applying keyframe-driven animations with configurable easing curves. The runtime renders animated characters using textured meshes from a packed atlas, supporting GPU-accelerated display across multiple platforms. The library provides animation blending and crossfading for smooth pose transitions between animations, and it allows switching a character’s appearance on the fly by applying different sk
C++2danimationsgame-dev
View on GitHub4,997
ogrecave/ogre
OGRECave/ogre
4,607View on GitHub
Ogre is a high-level 3D rendering engine designed for creating games, simulations, and visualizations without requiring low-level graphics API code. It functions as a framework for real-time 3D graphics processing, providing a physically based renderer to simulate lifelike surfaces and lighting. The engine includes specialized systems for skeletal animation to control character movement and a terrain generation system for producing large textured landscapes. These features are supported by automatic levels of detail and distance-based mesh management to maintain performance. The project cove
C++
View on GitHub4,607
hvision-nku/storydiffusion
HVision-NKU/StoryDiffusion
6,430View on GitHub
StoryDiffusion is a generative AI system designed for consistent character image and video generation. It utilizes a pluggable cross-attention module to inject shared character representations into pretrained diffusion models, allowing for visual identity stability across multiple images and scenes without retraining the base model. The project features a video generation pipeline that produces temporally coherent sequences from text prompts or condition images. It employs a latent space motion interpolator to predict intermediate frames and semantic motion, enabling long-range video generati
Jupyter Notebook
View on GitHub6,430
facebookresearch/animateddrawings
facebookresearch/AnimatedDrawings
12,797View on GitHub
AnimatedDrawings is a system for transforming static 2D drawings of humanoid figures into animated characters. It provides a workflow for character rigging, motion mapping, and scene assembly to turn hand-drawn sketches into moving visual sequences. The project utilizes a motion retargeting framework to map movement data from motion capture files onto custom character skeletons regardless of their physical proportions. It employs a rigging tool that uses pose estimation to automatically predict joint locations and create digital skeletons, which can be manually refined to improve animation ac
Python
View on GitHub12,797

See all 24 alternatives to AI4Animation

sebastianstarkeAI4Animation

Features

Open-source alternatives to AI4Animation

EsotericSoftware/spine-runtimes

OGRECave/ogre

HVision-NKU/StoryDiffusion

facebookresearch/AnimatedDrawings

Star history

Open-source alternatives to AI4Animation

EsotericSoftware/spine-runtimes

OGRECave/ogre

HVision-NKU/StoryDiffusion

facebookresearch/AnimatedDrawings