Scripts to create vector fields and flow maps that can be used in Unreal Engine 4 or Unity 3D for particle VFX.

Vector-Field-Navigation(Pathfinding) for Godot 4

为了实现真正的All in Local！ 我将Llava视觉大模型、QWen2.5-VL多模态大模型，以及STT和TTS模型全部部署在本地计算机上，打造了一个完全离线的机器人视觉交互系统。 机器人通过摄像头感知周围环境，LLaVA和QWen2.5-VL进行视觉分析，STT进行语音识别，TTS进行语音播报，整个过程完全在本地完成。

[ICCV-2025] TurboReg: TurboClique for Robust and Efficient Point Cloud Registration

[ICCV 2021] CPD with Local Surface Geometry (LSG-CPD)

Generalizing Spatial Transformers to Projective Geometry with Applications to 2D/3D Registration

Minimal solvers for calibrated camera pose estimation

This repo contains a curative list of homography estimation, image alignment and related application.

Neural-Guided RANSAC for Estimating Epipolar Geometry from Sparse Correspondences

C++ implementation of the Coherent Point Drift point set registration algorithm.

Implementations of the robust point set registration algorithm described in "Robust Point Set Registration Using Gaussian Mixture Models", Bing Jian and Baba C. Vemuri, IEEE Transactions on Pattern…

Python package for point cloud registration using probabilistic model (Coherent Point Drift, GMMReg, SVR, GMMTree, FilterReg, Bayesian CPD)

try to implement halcon shape based matching, refer to machine vision algorithms and applications, page 317 3.11.5, written by halcon engineers

Node-based Visual Programming Toolbox

PASTA: Learning Parameter-specific Affine Transformation for Medical Images Registration

the GPU implementation of bucket based farthest point sampling, achieves 3-4x speedup than the conventional implementation

Python efficient farthest point sampling (FPS) library. Compatible with numpy.

Code release for CVPR'23 paper - "Sphere-Guided Training of Neural Implicit Surfaces"

Official implementation of CVPR2024 - MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation

PyTorch code and models for the DINOv2 self-supervised learning method.

TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.

A unified framework for 3D content generation.

🏠 [ECCV 2024] Pytorch implementation of 'HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression'

A collection of papers on diffusion models for 3D generation.

A Unified Framework for Surface Reconstruction

😎 A curated list of awesome collision detection libraries and resources

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.