mlsanityData to 7 Oct 2026

Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning

arXiv 2602.05321 ↗First posted 5 Feb 2026cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We present Wid3R, a feed-forward neural network for multi-view visual geometry reconstruction that supports wide field-of-view camera models. Unlike existing methods that assume rectified or pinhole inputs, Wid3R directly models wide-angle imagery without explicit calibration or undistortion. Our approach leverages a ray-based representation with spherical harmonics and introduces a novel camera model token to enable distortion-aware reconstruction. To the best of our knowledge, Wid3R is the first multi-frame feed-forward 3D reconstruction method that supports 360 imagery. Moreover, we show that conditioning on diverse camera types improves generalization to 360 scenes and alleviates data sparsity issues. Wid3R achieves significant performance gains, improving AUC@30 by up to +33.67 on Zip-NeRF (fisheye) and +77.33 on Stanford2D3D (360).

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 68 of its 97 references that are in the map. First posted on arXiv 5 Feb 2026.

Builds on

68 of 97 references.

References · 68

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  7. 2021Vision Transformers for Dense Predictioncited by 1,789
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  9. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  10. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  11. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  12. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
38 more
  1. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  2. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  3. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  4. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  5. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  6. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 593
  7. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  8. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  9. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  10. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  11. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  12. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  13. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  14. 2020Virtual KITTI 2cited by 345
  15. 2023RoMa: Robust Dense Feature Matchingcited by 296
  16. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  17. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 292
  18. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
  19. 2020Softmax Splatting for Video Frame Interpolationcited by 276
  20. 20243D Reconstruction with Spatial Memorycited by 269
  21. 2024Global Structure-from-Motion Revisitedcited by 215
  22. 2023Project Aria: A New Tool for Egocentric Multi-Modal AI Researchcited by 201
  23. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  24. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
  25. 2025MUSt3R: Multi-view Network for Stereo 3D Reconstructioncited by 139
  26. 2021UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimationcited by 91
  27. 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 91
  28. 2023PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigationcited by 77
  29. 2023Detector-Free Structure from Motioncited by 71
  30. 2023SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Explorationcited by 62
  31. 2021360MonoDepth: High-Resolution 360deg Monocular Depth Estimationcited by 60
  32. 2025UniK3D: Universal Camera Monocular 3D Estimationcited by 60
  33. 2018The Double Sphere Camera Modelcited by 50
  34. 2023EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimationcited by 42
  35. 2021ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimationcited by 39
  36. 2024Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentationcited by 38
  37. 2025Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Cameracited by 38
  38. 2023HRDFuse: Monocular 360degDepth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributionscited by 37

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Camerascited by 3
  2. 2026PanoSeg3R: Feed-Forward 3D Semantic Segmentation for Panoramic Images with an Automatic Data Curation Pipelinecited by 1
  3. 2026Many Eyes, One World: Feed-Forward 3D Reconstruction from Mixed Camerascited by 0