Official implementation of "Understanding multi-view transformers" (ICCV 2025 E2E3D Workshop)
☆51Feb 10, 2026Updated 8 months ago
Alternatives and similar repositories for und3rstand
Users that are interested in und3rstand are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- logit lens for VGGT☆28Dec 2, 2025Updated 11 months ago
- [ECCVW 2026] RoMa-Ω: What Feed-Forward 3D Models Know About Image Matching☆69Sep 10, 2026Updated last month
- Official implementation of MVAP-G [ECCV'26 Oral]☆13Jul 23, 2026Updated 3 months ago
- [LIMIT@ECCV 2026] RIPE, minus the negatives, plus a trainable matcher - full sparse matching pipelines learned from positive image pairs …☆34Sep 2, 2026Updated 2 months ago
- [ECCV 2026] ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views☆37Sep 14, 2026Updated last month
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Code for "Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations"☆17Mar 9, 2026Updated 7 months ago
- [Emergent Multi-View Geometry Through Self-Distillation]: 3D SSL through multi-view self-distillation, called Poincar3☆50Oct 5, 2026Updated last month
- [CVPR 2026] Emergent Extreme-View Geometry in 3D Foundation Models☆28Aug 25, 2026Updated 2 months ago
- Tutorial examples and sample applications for DC-SAM.☆20Mar 4, 2026Updated 8 months ago
- Repository for "Processing and acquisition traces in visual encoders: What does CLIP know about your camera?" and "Invisible Shortcuts: W…☆17Aug 7, 2026Updated 3 months ago
- [CVPR 2026 Highlight] MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction☆43Jun 1, 2026Updated 5 months ago
- REDI-Match: Fast and rotation-robust dense image matching designed for efficient real-world deployment.☆50Aug 24, 2026Updated 2 months ago
- [CVPR '25] MEt3R: Measuring Multi-View Consistency in Generated Images☆200Feb 23, 2026Updated 8 months ago
- Cameras as Relative Positional Encoding☆770Dec 18, 2025Updated 10 months ago
- 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.
- AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration (ICCV 2025)☆248Sep 4, 2026Updated 2 months ago
- [NeurIPS 2026] BA-T: An Iterative Transformer for Two-View Bundle Adjustment☆49Oct 22, 2026Updated 2 weeks ago
- [ECCV '26] Code for paper "RayRoPE: Projective Ray Positional Encoding for Multi-view Attention"☆179Sep 23, 2026Updated last month
- Spherical Structure-from-Motion in C++☆52Nov 14, 2025Updated 11 months ago
- Official repository of the CVPR24 paper "The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement"☆60Aug 10, 2024Updated 2 years ago
- ☆33Jul 27, 2026Updated 3 months ago
- A fast and simple structure from motion pipeline written in Pytorch.☆292Mar 13, 2026Updated 7 months ago
- UFM: A Unified Dense Image Correspondence Estimator for both Optical Flow & Wide Baseline Matching Tasks. Matches any pair of images. (Ne…☆362Oct 15, 2026Updated 3 weeks ago
- What VGGT Knows About Overlap — probing frozen geometric foundation models for co-visibility (Co-VGGT, ECCV 2026). Code coming soon.☆18Jun 22, 2026Updated 4 months ago
- 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.
- Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views☆731May 1, 2025Updated last year
- NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization, CVPR2023☆66Nov 16, 2023Updated 2 years ago
- Official repository for "AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos" (CVPR 2025)☆309May 7, 2025Updated last year
- ☆10Oct 8, 2026Updated 3 weeks ago
- Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features☆108Apr 8, 2025Updated last year
- [WACV 2027] Semi-Dense Matching Uncertainty Is Not Just Local Confidence 🎯☆38Oct 18, 2026Updated 3 weeks ago
- [NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"☆498Sep 19, 2025Updated last year
- [ICML 2026] 4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere☆261Jul 7, 2026Updated 4 months ago
- Dynamic 3D Foundation Model using Causal Transformer. [ICLR 2026]☆414May 8, 2026Updated 5 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- An operation trying to do the opposite of F.grid_sample☆20Aug 8, 2023Updated 3 years ago
- ☆10Sep 30, 2026Updated last month
- Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"☆449Nov 24, 2025Updated 11 months ago
- Arbitrary Reconstruction and Tracking of 4D Observation in the Wild☆127Updated this week
- Public code for XFactor: Introduces the first geometry-free model to achieve true self-supervised / pose-free Novel View Synthesis (NVS) …☆167May 11, 2026Updated 5 months ago
- Official Code for "Can These Views Be One Scene?"☆23May 22, 2026Updated 5 months ago
- 🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.☆802Nov 5, 2025Updated last year