initialneil
Follow
Stars
Official implementation for the SIGGRAPH Asia 2024 paper SPARK: Self-supervised Personalized Real-time Monocular Face Capture
HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior
A geometry-shader-based, global CUDA sorted high-performance 3D Gaussian Splatting rasterizer. Can achieve a 5-10x speedup in rendering compared to the vanialla diff-gaussian-rasterization.
Implementation of "Large Steps in Inverse Rendering of Geometry"
Speech To Speech: an effort for an open-sourced and modular GPT4-o
DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models
[CVPR 2024] AMUSE: Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion
Implementation of "Learning to Make Keypoints Sub-Pixel Accurate" (ECCV 2024).
The Kalibr visual-inertial calibration toolbox
code for "PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction"
Official implementation of Diffusion Autoencoders
Implementation code：Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
📖 A curated list of resources dedicated to talking face.
Use OpenAI TTS(Text to Speech) API with Gradio
Robust Speech Recognition via Large-Scale Weak Supervision
Three.js-based implementation of 3D Gaussian splatting
CVPR'24, Official Codebase of our Paper: "Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation".
[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
[CVPR 2024] Official repository for "Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians"
Measures and metrics for image2image tasks. PyTorch.
Dynamic Gaussian Mesh: Consistent Mesh Reconstruction from Monocular Videos
[CVPR 2024] Code for SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
[CVPR 2024] Official Code for "AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"
NeurIPS-2021: Direct Multi-view Multi-person 3D Human Pose Estimation