Representation learning for sketches; addresses long stroke sequence reconstructions and interpolation, with SoTA results in classification and SBIR

The official implementation of the NeurIPS 2024 paper: DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus

Code for Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data, ICCV 2019

Pytorch code to construct a 3D point cloud model from single RGB image.

A deep learning model to spot the actions in soccer videos by unifying global and local features

Algorithm and data structure articles for https://cp-algorithms.com (based on http://e-maxx.ru)

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Applied 3D geometry in C++, with a focus on surface meshes.

A collection of 3D reconstruction papers in the deep learning era.

Build high-quality Laplace matrices on meshes and point clouds in Python. Implements [Sharp & Crane SGP 2020].

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

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