0iui0's repositories
dm-vio
Source code for the paper DM-VIO: Delayed Marginalization Visual-Inertial Odometry
AGI-Samantha
AGI has been achieved externally
AnimateDiff
Official implementation of AnimateDiff.
AppAgent
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
CogVLM
a state-of-the-art-level open visual language model | 多模态预训练模型
DemoFusion
Let us democratise high-resolution generation! (arXiv 2023)
Depth-Anything
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
EgoThink
The official code and data for paper "Can Vision-Language Models Think from a First-Person Perspective?"
embodied-generalist
Official code repository for 3D Embodied Generalist LEO
gaussian-head
Official repository for 'GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation'
generative-models
Generative Models by Stability AI
home-robot
Mobile manipulation research tools for roboticists
HumanGaussian
Github Repo for "HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting"
Instant-angelo
Instant-angelo: Build high-fidelity Digital Twin within 20 Minutes!
magic-animate
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
MiniCPM
MiniCPM-2B: An end-side LLM outperforms Llama2-13B.
OmniLMM
Large Multi-modal Models for Strong Performance and Efficient Deployment
Osprey
The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"
OVSG
[CoRL2023] Open-Vocabulary Scene-Graph
SAM-Graph
Code for "SAM-guided Graph Cut for 3D Instance Segmentation"
SuGaR
Official implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering
SwiftInfer
Efficient AI Inference & Serving
TEASER-plusplus
A fast and robust point cloud registration library
tensorrtx
Implementation of popular deep learning networks with TensorRT network definition API
ultralytics
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
vision_msgs
Algorithm-agnostic computer vision message types for ROS.
YOLOv8-TensorRT
YOLOv8 using TensorRT accelerate !
zed-open-capture
Low level camera driver for the ZED stereo camera family. API docs available here: