Accelerate VGGT with efficient desciptor-based global attention
☆98Jun 3, 2026Updated 2 months ago
Alternatives and similar repositories for FlashVGGT
Users that are interested in FlashVGGT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICME 26] S-VGGT: Structure-Aware Subscene Decomposition for Scalable 3D Foundation Models☆33Mar 19, 2026Updated 4 months ago
- [ICLR 2026] Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos☆30May 29, 2026Updated 2 months ago
- [ICLR 2026] FastVGGT: Fast Visual Geometry Transformer☆809Jan 28, 2026Updated 6 months ago
- The official implementation of InfiniteVGGT☆381Apr 19, 2026Updated 3 months ago
- [CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training☆490Jun 11, 2026Updated last month
- 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.
- GLUEMAP: Global Structure-from-Motion Meets Feedforward Reconstruction☆330Jun 22, 2026Updated last month
- Geometry-grounded Point Transformer (CVPR 2026)☆147May 6, 2026Updated 3 months ago
- A unified framework for feed-forward neural networks☆15Nov 28, 2025Updated 8 months ago
- Self-Improving 4D Perception via Self-Distillation☆72Apr 10, 2026Updated 4 months ago
- [CVPR 2026 Findings] Speed3R: Sparse Feed-forward 3D Reconstruction Models☆77Apr 7, 2026Updated 4 months ago
- [CVPR 2026 Findings] SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes☆95Nov 25, 2025Updated 8 months ago
- VGGT-X: When VGGT Meets Dense Novel View Synthesis☆320Feb 4, 2026Updated 6 months ago
- VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction☆46May 29, 2026Updated 2 months ago
- [CVPR 2026] Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers☆103Jun 24, 2026Updated last month
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Official code for CVPR 2026 paper: VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection☆152Jul 15, 2026Updated 3 weeks ago
- [CVPR 2026] Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction☆80Mar 18, 2026Updated 4 months ago
- The official implementation of the paper “VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction.”☆268Dec 2, 2025Updated 8 months ago
- 🚀 Official code for “XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression”, …☆47Jan 27, 2026Updated 6 months ago
- [CVPR 2026] LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging☆222Feb 28, 2026Updated 5 months ago
- Code for Implicit Visual Geometry Transformer (IVGT)☆62May 27, 2026Updated 2 months ago
- ☆20Dec 25, 2025Updated 7 months ago
- Depth-Guided Scale-Aware Global Structure-from-Motion☆24Jul 10, 2026Updated last month
- [CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction☆521May 11, 2026Updated 2 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- [CVPR 26] Release repo of our work "Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers"☆193May 18, 2026Updated 2 months ago
- ☆93Apr 21, 2026Updated 3 months ago
- [Arxiv'25] SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images☆50Oct 18, 2025Updated 9 months ago
- VGGT optimized for VRAM usage - 6x less VRAM, 150 images in 8GB, 1100 images in 32GB☆73Aug 10, 2025Updated last year
- [CVPR'26] Official code for the paper "VGG-T³: Offline Feed-Forward 3D Reconstruction at Scale"☆187May 25, 2026Updated 2 months ago
- [ECCV 2026] One4D: Unified 4D Generation and Reconstruction☆116Jun 18, 2026Updated last month
- [ICLR 2026] A simple state update rule to enhance length generalization for CUT3R☆722May 11, 2026Updated 2 months ago
- [CVPR'26 Highlight] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend☆479Jun 5, 2026Updated 2 months ago
- M³: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM☆83Mar 18, 2026Updated 4 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [CVPR 2026 Hightlight] OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer☆361May 21, 2026Updated 2 months ago
- ☆51Jun 12, 2026Updated last month
- Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction☆409Jun 1, 2026Updated 2 months ago
- Official implement of VGGT-Long☆893Mar 20, 2026Updated 4 months ago
- [ICLR 2026] Code for QuantVGGT: Quantized Visual Geometry Grounded Transformer☆119Mar 20, 2026Updated 4 months ago
- ☆17Updated this week
- [CVPR 2026] Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction☆367Mar 20, 2026Updated 4 months ago