Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

[NeurIPS'25] Official repository of Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

Reference PyTorch implementation and models for DINOv3

Stereo4D dataset and processing code

[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

Aria Training and Evaluation Kit

HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos, CVPR 2025

projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data.

The official Meta Llama 3 GitHub site

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Cramming the training of a (BERT-type) language model into limited compute.

Robust Speech Recognition via Large-Scale Weak Supervision

A library for differentiable nonlinear optimization

Aria data tools provide the open-source toolkit in C++ and Python to interact with data from Project Aria

[TensorFlow] Official implementation of CVPR'20 oral paper - D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features https://arxiv.org/abs/2003.03164

Cost Volume Pyramid Based Depth Inference for Multi-View Stereo (CVPR 2020 Oral)

[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation

[BMVC 2020 Oral] Bipartite Graph Reasoning GANs for Person Image Generation

[ECCV 2020] XingGAN for Person Image Generation

TensorFlow implementation of GeoDesc (ECCV'18), ContextDesc (CVPR'19) and ASLFeat (CVPR'20)

Implementation of CVPR'20 paper - ASLFeat: Learning Local Features of Accurate Shape and Localization

KFNet: Learning Temporal Camera Relocalization using Kalman Filtering (CVPR 2020 Oral)

Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE

BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks

Implementation of ICCV19 Paper "Learning Two-View Correspondences and Geometry Using Order-Aware Network"

Code for "Point-based Multi-view Stereo Network" (ICCV 2019 Oral) & "Visibility-aware Point-based Multi-view Stereo Network" (TPAMI)

AttentionGAN for Unpaired Image-to-Image Translation & Multi-Domain Image-to-Image Translation

[CVPR 2019 Oral] Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation