Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11, YOLOv12 for ROS 2

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

A collection of resources and papers on Diffusion Models

Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model

Reproduce partial features of DeePMD-kit using PyTorch.

Official PyTorch implementation for paper`Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection' accepted by CVPR 2023

Fast Segment Anything

Official code repository for NeurIPS 2022 paper "Chaotic Dynamics are Intrinsic to Neural Network Training with SGD"

Code for "TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential"

NTU-X, which is an extended version of popular NTU dataset

[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"

Must-read papers on prompt-based tuning for pre-trained language models.

Official PyTorch implementation for the paper "CARD: Classification and Regression Diffusion Models"

Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification (TPAMI 2022)

Official source code of FreeCAD, a free and opensource multiplatform 3D parametric modeler.

[CVPR2022] Decoupling Makes Weakly Supervised Local Feature Better

[ICLR 2022] Official implementation of the paper "DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR"

Making large AI models cheaper, faster and more accessible

Piccolo (formerly Pilot) – mini game engine for games104

Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization

A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package

[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

Code for a series of work in LiDAR perception, including SST (CVPR 22), FSD (NeurIPS 22), FSD++ (TPAMI 23), FSDv2, and CTRL (ICCV 23, oral).

A curated list of awesome neural radiance fields papers

[TPAMI 2024] This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.