[CVPR 2026] DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
☆66Apr 15, 2026Updated 6 months ago
Alternatives and similar repositories for DAGE
Users that are interested in DAGE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [SIGGRAPH Asia 2026] M³: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM☆91Nov 2, 2026Updated last week
- [CVPR'26 Highlight] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend☆515Jun 5, 2026Updated 5 months ago
- The official implementation of InfiniteVGGT☆397Apr 19, 2026Updated 6 months ago
- [ECCV 2026] Syn4D: A Multiview Synthetic 4D Dataset☆156Sep 1, 2026Updated 2 months ago
- Geometry-grounded Point Transformer (CVPR 2026)☆157Sep 11, 2026Updated 2 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.
- ☆103Jun 3, 2026Updated 5 months ago
- Official implementation of "Repurposing Geometric Foundation Models for Multi-view Diffusion"☆280Jul 24, 2026Updated 3 months ago
- [ICLR 2026] NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction☆173Jun 13, 2026Updated 5 months ago
- [CVPR 2026] "E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training" official implementation.☆317Oct 10, 2026Updated last month
- Building Rome from a Single Image: metric 3D scene meshes from one photograph☆51Oct 10, 2026Updated last month
- VDPP: Video Depth Post-Processing for Speed and Scalability☆13Apr 9, 2026Updated 7 months ago
- [CVPR 2026 Hightlight] OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer☆385May 21, 2026Updated 5 months ago
- ViGeo: Towards Consistent Video Geometry Estimation☆143Oct 15, 2026Updated 3 weeks ago
- Official implementation paper OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields☆133Jul 12, 2026Updated 4 months ago
- 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.
- PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation☆30Aug 27, 2026Updated 2 months ago
- GAC3D: Improving Monocular 3D Object Detection with Ground-Guide Model and Adaptive Convolution (PeerJ)☆14Aug 26, 2021Updated 5 years ago
- Official implementation of ICLR26 paper "G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior"☆175May 24, 2026Updated 5 months ago
- [CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training☆515Jun 11, 2026Updated 5 months ago
- [CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning☆364Apr 18, 2026Updated 6 months ago
- [ICLR2026] Official Implementation of "Dens3R: A Foundation Model for 3D Geometry Prediction"☆403May 14, 2026Updated 5 months ago
- [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning☆2,253Jul 3, 2026Updated 4 months ago
- Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction☆527Sep 25, 2026Updated last month
- Official code of ''AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting''☆17May 21, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [NeuIPS 2026] Official Repo of "Glob3R: Global Structure-from-Motion with 3D Foundation Models"☆287Oct 13, 2026Updated last month
- [ICLR2026] Large Depth Completion Model from Sparse Observations☆65Oct 17, 2026Updated 3 weeks ago
- Official implement of VGGT-Long☆912Mar 20, 2026Updated 7 months ago
- [CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction☆549Sep 15, 2026Updated last month
- [NeurIPS 2026] Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".☆443Sep 24, 2026Updated last month
- [ECCV 2026] FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction☆15Jun 27, 2026Updated 4 months ago
- ☆92Feb 27, 2026Updated 8 months ago
- [WACV 2027] Mem3R: Streaming 3D Reconstruction with Hybrid Memory.☆55Oct 25, 2026Updated 2 weeks ago
- WorldTree: Towards 4D Dynamic Worlds from Monocular Video using Tree-Chains (ICLR2026)☆23Mar 14, 2026Updated 8 months ago
- 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.
- MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry☆54Mar 14, 2026Updated 7 months ago
- [CVPR 2026 Findings] Speed3R: Sparse Feed-forward 3D Reconstruction Models☆82Nov 6, 2026Updated last week
- The first "ImageNet" 3D dataset.☆108Aug 25, 2026Updated 2 months ago
- [ECCVW 2026] RoMa-Ω: What Feed-Forward 3D Models Know About Image Matching☆71Sep 10, 2026Updated 2 months ago
- [3DV 2026 Oral] Official Repo of "SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization"☆301Feb 23, 2026Updated 8 months ago
- This is the repo for paper "OccSim: Multi-kilometer Simulation with Long-horizon Occupancy World Models"☆20Sep 21, 2026Updated last month
- [ICLR 2026] FastVGGT: Fast Visual Geometry Transformer☆824Jan 28, 2026Updated 9 months ago
Are these results useful?