[CVPR 2026] LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging
☆240Feb 28, 2026Updated 8 months ago
Alternatives and similar repositories for LiteVGGT-repo
Users that are interested in LiteVGGT-repo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2026] FastVGGT: Fast Visual Geometry Transformer☆825Jan 28, 2026Updated 9 months ago
- The official implementation of InfiniteVGGT☆397Apr 19, 2026Updated 7 months ago
- [ICLR 2026] Streaming 4D Visual Geometry Transformer☆994Oct 27, 2025Updated last year
- [CVPR 2026] Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction☆87Mar 18, 2026Updated 8 months ago
- The official implementation of the paper “VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction.”☆284Dec 2, 2025Updated 11 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [ICLR 2026] Code for QuantVGGT: Quantized Visual Geometry Grounded Transformer☆126Mar 20, 2026Updated 8 months ago
- [CVPR 2026] Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers☆107Jun 24, 2026Updated 4 months ago
- Official implement of VGGT-Long☆914Mar 20, 2026Updated 8 months ago
- Accelerate VGGT with efficient desciptor-based global attention☆102Jun 3, 2026Updated 5 months ago
- [CVPR'26 Highlight] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend☆516Jun 5, 2026Updated 5 months ago
- [CVPR 2026 Findings] SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes☆102Nov 25, 2025Updated 11 months ago
- [CVPR 26] Release repo of our work "Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers"☆200May 18, 2026Updated 6 months ago
- [ECCV 2026] OVGGT is a training-free framework enabling streaming 3D reconstruction from arbitrarily long video with constant memory.☆59Sep 2, 2026Updated 2 months ago
- VGGT optimized for VRAM usage - 6x less VRAM, 150 images in 8GB, 1100 images in 32GB☆75Aug 10, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [CVPR'26] Official implementation of "Emergent Outlier View Rejection in Visual Geometry Grounded Transformers"☆228Feb 22, 2026Updated 8 months ago
- [CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training☆516Jun 11, 2026Updated 5 months ago
- [CVPR'2026]: MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer☆91Apr 21, 2026Updated 6 months ago
- VGGT-X: When VGGT Meets Dense Novel View Synthesis☆331Feb 4, 2026Updated 9 months ago
- Official code repository for MGSD: Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation.☆23Jun 5, 2026Updated 5 months ago
- [ACCV 2026 Oral] DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion☆35Sep 30, 2026Updated last month
- [CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction☆552Sep 15, 2026Updated 2 months ago
- [NeurIPS 2025] the official project page of a paper, "PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splattin…☆77Oct 25, 2026Updated 3 weeks ago
- [ICLR 2026] A simple state update rule to enhance length generalization for CUT3R☆741May 11, 2026Updated 6 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [CVPR 2026 Hightlight] OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer☆387May 21, 2026Updated 5 months ago
- [CVPR 2026 Findings] Speed3R: Sparse Feed-forward 3D Reconstruction Models☆82Nov 6, 2026Updated 2 weeks ago
- [ECCV 2026] Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers☆34Jul 7, 2026Updated 4 months ago
- VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold☆1,191Jun 29, 2026Updated 4 months ago
- [ECCV 2026] UniPR-3D☆49Jun 20, 2026Updated 5 months ago
- Geometry-grounded Point Transformer (CVPR 2026)☆158Sep 11, 2026Updated 2 months ago
- [IJCV'26] SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images☆55Oct 18, 2025Updated last year
- [CVPR 2026] Emergent Extreme-View Geometry in 3D Foundation Models☆28Aug 25, 2026Updated 2 months ago
- [ECCV 2026] SLAM-Former: Putting SLAM into One Transformer☆530Aug 10, 2026Updated 3 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [ACCV 2026] OTT3R: Multi-View 3D Reconstruction and Fast Dataset Generation at 1% Compute.☆17Oct 14, 2026Updated last month
- [ICCV 2025 Oral] RePoseD: Efficient Relative Pose Estimation With Known Depth Information☆40Jan 12, 2026Updated 10 months ago
- MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry☆53Mar 14, 2026Updated 8 months ago
- [SIGGRAPH Asia 2026] M³: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM☆92Nov 2, 2026Updated 2 weeks ago
- HorizonStream Official Implementation☆260Oct 21, 2026Updated 3 weeks ago
- ☆11Oct 8, 2026Updated last month
- [CVPR 2026] Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction☆89Oct 9, 2026Updated last month
Are these results useful?