[ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning
☆1,735Mar 13, 2026Updated last week
Alternatives and similar repositories for Pi3
Users that are interested in Pi3 are comparing it to the libraries listed below
Sorting:
- Official implementation of Continuous 3D Perception Model with Persistent State☆1,368Aug 27, 2025Updated 6 months ago
- [ICLR 2026] Streaming 4D Visual Geometry Transformer☆849Oct 27, 2025Updated 4 months ago
- [ICLR2026] Official Implementation of "Dens3R: A Foundation Model for 3D Geometry Prediction"☆372Sep 29, 2025Updated 5 months ago
- [ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"☆516Aug 4, 2025Updated 7 months ago
- ☆709May 1, 2025Updated 10 months ago
- Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"☆1,344Jun 16, 2025Updated 9 months ago
- [ICCV 2025] A simple training-free approach adapting DUSt3R for dynamic scenes.☆515Apr 1, 2025Updated 11 months ago
- Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"☆1,254Jan 5, 2026Updated 2 months ago
- [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision☆2,367Nov 2, 2025Updated 4 months ago
- [CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass☆1,527May 7, 2025Updated 10 months ago
- Grounding Image Matching in 3D with MASt3R☆2,797Jun 30, 2025Updated 8 months ago
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction☆2,972Jan 18, 2026Updated 2 months ago
- [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling☆580Oct 26, 2025Updated 4 months ago
- 🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.☆788Nov 5, 2025Updated 4 months ago
- [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer☆12,641Mar 3, 2026Updated 2 weeks ago
- Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page …☆581Updated this week
- [ICLR 2026] FastVGGT: Fast Visual Geometry Transformer☆714Jan 28, 2026Updated last month
- Official implement of VGGT-Long☆811Updated this week
- [3DV'25] 3D Reconstruction with Spatial Memory☆1,121Feb 25, 2025Updated last year
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆444Feb 25, 2026Updated 3 weeks ago
- [ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy☆929Feb 27, 2026Updated 3 weeks ago
- [SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views☆763Dec 22, 2025Updated 3 months ago
- [ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images☆934Feb 25, 2026Updated 3 weeks ago
- ViPE: Video Pose Engine for Geometric 3D Perception☆1,792Jan 1, 2026Updated 2 months ago
- [CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R☆1,110Oct 18, 2025Updated 5 months ago
- [CVPR 2025] "DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion" official implementation.☆183Jul 7, 2025Updated 8 months ago
- [NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"☆413Sep 19, 2025Updated 6 months ago
- A simple state update rule to enhance length generalization for CUT3R☆609Oct 1, 2025Updated 5 months ago
- Cameras as Relative Positional Encoding☆690Dec 18, 2025Updated 3 months ago
- [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control☆1,303Sep 24, 2025Updated 5 months ago
- 🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images☆1,210Aug 27, 2025Updated 6 months ago
- [CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth☆1,161Apr 27, 2025Updated 10 months ago
- Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs☆780Nov 23, 2024Updated last year
- DUSt3R: Geometric 3D Vision Made Easy☆7,011Sep 24, 2025Updated 5 months ago
- [CVPR 2025 Highlight] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos☆456Apr 4, 2025Updated 11 months ago
- [CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models☆1,114Jun 28, 2025Updated 8 months ago
- [DEPRECATED] GLOMAP - Global Structured-from-Motion Revisited☆2,290Jan 30, 2026Updated last month
- MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025)☆490Jul 9, 2025Updated 8 months ago
- [CVPR 2026] Official implementation of "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second".☆419Updated this week