Structured3D alternatives for AI agents.

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes

ScanNet/ScanNet is a high-star GitHub project relevant to AI agent workflows.

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

Interactive Image Generation via Generative Adversarial Networks

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

Dataset Management Framework, a Python library and a CLI tool to build, analyze and manage Computer Vision datasets.

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Scenic: A Jax Library for Computer Vision Research and Beyond

A python library for self-supervised learning on images.

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Demo for the "Talking Head Anime from a Single Image."

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

An open source library and framework for deep learning on satellite and aerial imagery.

Ray tracing and hybrid rasterization of Gaussian particles

记录cv算法工程师的成长之路，分享计算机视觉和模型压缩部署技术栈笔记。https://harleyszhang.github.io/cv_note/

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.