Arbitrary Reconstruction and Tracking of 4D Observation in the Wild
☆127Nov 3, 2026Updated this week
Alternatives and similar repositories for arrow
Users that are interested in arrow are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official implementation paper OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields☆132Jul 12, 2026Updated 3 months ago
- Point4D: Long-range 4D Motion Reconstruction (NeurIPS 2026 Spotlight)☆102Sep 9, 2026Updated last month
- [Emergent Multi-View Geometry Through Self-Distillation]: 3D SSL through multi-view self-distillation, called Poincar3☆50Oct 5, 2026Updated last month
- NeurIPS 2026☆100Oct 29, 2026Updated last week
- Code repository for "TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations"☆491Oct 28, 2026Updated last week
- 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.
- Efficient data storage format optimized for random-access reads, especially in machine learning workflows☆26Updated this week
- [ACCV 2026 Oral] DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion☆34Sep 30, 2026Updated last month
- Multithread python pipeline framework☆13Dec 26, 2025Updated 10 months ago
- [ICML 2026] 4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere☆261Jul 7, 2026Updated 3 months ago
- Code for SM4RT: Learning Structured Motion Geometry for 4D Reconstruction☆147Aug 19, 2026Updated 2 months ago
- The official implementation of 'S4VY: Segment Anything in Feed-Forward 4D Visual Geometry'☆174Oct 30, 2026Updated last week
- [NeurIPS 2026 Spotlight] MoSE3: Learning World-Space SE(3) at Every Pixel☆199Oct 30, 2026Updated last week
- Solv3R: 3D Looped Transformer as a Multi-view Solver☆169Updated this week
- [ECCV 2026] Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels☆344Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation☆76Jun 5, 2026Updated 5 months ago
- Implementation of D4RT, Efficiently Reconstructing Dynamic Scenes, from Deepmind☆74Jun 20, 2026Updated 4 months ago
- ☆92Feb 27, 2026Updated 8 months ago
- Official implementation of Video-DPM☆262Jan 19, 2026Updated 9 months ago
- Code for the ICML 2026 paper "SG2Loc: Sequential Visual Localization on 3D Scene Graphs"☆11Jul 26, 2026Updated 3 months ago
- [CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training☆514Jun 11, 2026Updated 4 months ago
- [NeurIPS 2026 - Oral] Official implementation of Surflo: Consistent 3D Surface Flow Model with Global State.☆460Sep 30, 2026Updated last month
- Any4D: Unified Feed-Forward Metric 4D Reconstruction☆422Apr 17, 2026Updated 6 months ago
- [CVPR 2026] Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers☆106Jun 24, 2026Updated 4 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.
- InfiniSplat Series: Feed-Forward 3D Gaussian Reconstruction☆587Updated this week
- ☆22Jul 30, 2026Updated 3 months ago
- [SIGGRAPH Asia 2026] RealMe: Immersive Volumetric Video from Minimal Captures☆43Oct 22, 2026Updated 2 weeks ago
- [ECCV 2026 Long Oral] Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding☆195Sep 15, 2026Updated last month
- Cameras as Relative Positional Encoding☆770Dec 18, 2025Updated 10 months ago
- Gen4P: Video Generators are 4D Perceivers☆38Oct 16, 2026Updated 3 weeks ago
- Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction☆488Sep 25, 2026Updated last month
- TAPIP3D: Tracking Any Point in Persistent 3D Geometry☆430Dec 28, 2025Updated 10 months ago
- [ACM MM 2026] PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training☆72Oct 19, 2026Updated 2 weeks 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.
- Official implementation of our paper "EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder"☆13Oct 6, 2026Updated last month
- Self-Improving 4D Perception via Self-Distillation☆80Apr 10, 2026Updated 6 months ago
- [NeurIPS 2026] World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Videos☆38Oct 18, 2026Updated 2 weeks ago
- [ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking☆525Updated this week
- ☆1,010Updated this week
- [ICML'26] PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation☆242Sep 6, 2026Updated 2 months ago
- [ECCV 2026] Official repository for "Boosting 3D Foundation Models with Edge-Based Pose Optimization".☆116Oct 29, 2026Updated last week