mlsanityData to 14 Oct 2026

G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

arXiv 2508.11379 ↗First posted 15 Aug 2025cs.CV cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

We introduce G-CUT3R, a novel feed-forward approach for guided 3D scene reconstruction that enhances the CUT3R model by integrating prior information. Unlike existing feed-forward methods that rely solely on input images, our method leverages auxiliary data, such as depth, camera calibrations, or camera positions, commonly available in real-world scenarios. We propose a lightweight modification to CUT3R, incorporating a dedicated encoder for each modality to extract features, which are fused with RGB image tokens via zero convolution. This flexible design enables seamless integration of any combination of prior information during inference. Evaluated across multiple benchmarks, including 3D reconstruction and other multi-view tasks, our approach demonstrates significant performance improvements, showing its ability to effectively utilize available priors while maintaining compatibility with varying input modalities.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 32 of its 41 references that are in the map. First posted on arXiv 15 Aug 2025.

Builds on

32 of 41 references.

References · 32

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  5. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  6. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  7. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  8. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  9. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  10. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  12. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
20 more
  1. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  2. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  3. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  4. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  5. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  6. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  7. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  8. 2023Emergent Correspondence from Image Diffusioncited by 446
  9. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  10. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  11. 2021Neural RGB-D Surface Reconstructioncited by 313
  12. 2016LIFT: Learned Invariant Feature Transformcited by 306
  13. 20243D Reconstruction with Spatial Memorycited by 277
  14. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  15. 2019ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residualscited by 181
  16. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 115
  17. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 114
  18. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  19. 2022ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wildcited by 92
  20. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 72

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 11.

12 papers.

  1. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 20
  2. 2026Feed-Forward 3D Scene Modeling: A Problem-Driven Perspectivecited by 6
  3. 2026VGGT-SLAM++cited by 4
  4. 2026UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perceptioncited by 2
  5. 2026GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mappingcited by 1
  6. 2026MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localizationcited by 0
  7. 2026UniT: Unified Geometry Learning with Group Autoregressive Transformercited by 0
  8. 2026Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformerscited by 0
  9. 2026VI3: Grounding Pretrained 3D Foundation Models with Inertial Cuescited by 0
  10. 2026Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstructioncited by 0
  11. 2026Racing in Volume with Flow Ensemblescited by 0
  12. 2026AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backendcited by 0