Reference PyTorch implementation and models for DINOv3
☆11,006Jul 15, 2026Updated last week
Alternatives and similar repositories for dinov3
Users that are interested in dinov3 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- PyTorch code and models for the DINOv2 self-supervised learning method.☆13,157Jun 3, 2026Updated last month
- The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading t…☆11,081Jul 15, 2026Updated last week
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…☆19,595May 30, 2026Updated last month
- [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer☆14,002May 19, 2026Updated 2 months ago
- Depth Anything 3☆5,969Jul 15, 2026Updated last week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning☆2,088Jul 3, 2026Updated 3 weeks ago
- [DEIMv2] Real Time Object Detection Meets DINOv3☆1,948Mar 24, 2026Updated 4 months ago
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆2,329Apr 13, 2026Updated 3 months ago
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction☆3,591Jul 17, 2026Updated last week
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆4,392Mar 23, 2026Updated 4 months ago
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆1,901May 29, 2026Updated last month
- Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"☆1,978Feb 25, 2026Updated 5 months ago
- SAM 3D Objects☆7,171Jun 2, 2026Updated last month
- [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision☆2,686Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆19,664Jan 30, 2026Updated 5 months ago
- [NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation☆8,532Mar 24, 2026Updated 4 months ago
- The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoi…☆54,601Sep 18, 2024Updated last year
- ViPE: Video Pose Engine for Geometric 3D Perception☆2,050Jun 9, 2026Updated last month
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆3,655Nov 11, 2025Updated 8 months ago
- Official implementation of Continuous 3D Perception Model with Persistent State☆1,468Aug 27, 2025Updated 10 months ago
- [CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching☆2,837Dec 19, 2025Updated 7 months ago
- [ICLR 2026] Streaming 4D Visual Geometry Transformer☆943Oct 27, 2025Updated 8 months ago
- [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"☆10,443Aug 12, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image☆34,069Mar 25, 2026Updated 4 months ago
- Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)☆504Oct 24, 2025Updated 9 months ago
- Cameras as Relative Positional Encoding☆742Dec 18, 2025Updated 7 months ago
- [ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy☆984Feb 27, 2026Updated 4 months ago
- PyTorch implementation of JiT https://arxiv.org/abs/2511.13720☆2,468Dec 8, 2025Updated 7 months ago
- [CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass☆1,597May 7, 2025Updated last year
- [CVPR 2026 Oral] VGGT Omega☆3,676Jul 15, 2026Updated last week
- Grounding Image Matching in 3D with MASt3R☆3,052Jun 30, 2025Updated last year
- NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomou…☆11,243Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and …☆17,686Sep 5, 2024Updated last year
- [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos☆2,009Oct 7, 2025Updated 9 months ago
- DUSt3R: Geometric 3D Vision Made Easy☆7,261Sep 24, 2025Updated 10 months ago
- RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning…☆8,724Updated this week
- Self-supervised learning for spatial perception☆865Jul 8, 2026Updated 2 weeks ago
- [CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models☆1,510Dec 16, 2025Updated 7 months ago
- [ICLR '26 Oral] Official repository of the paper "AnyUp: Universal Feature Upsampling".☆569Apr 17, 2026Updated 3 months ago