mlsanityData to 7 Oct 2026

NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations

arXiv 2306.09109 ↗First posted 15 Jun 2023cs.CVcited by 53

Not on the map. Why?

Abstract (arXiv)

Recent advances in neural reconstruction enable high-quality 3D object reconstruction from casually captured image collections. Current techniques mostly analyze their progress on relatively simple image collections where Structure-from-Motion (SfM) techniques can provide ground-truth (GT) camera poses. We note that SfM techniques tend to fail on in-the-wild image collections such as image search results with varying backgrounds and illuminations. To enable systematic research progress on 3D reconstruction from casual image captures, we propose NAVI: a new dataset of category-agnostic image collections of objects with high-quality 3D scans along with per-image 2D-3D alignments providing near-perfect GT camera parameters. These 2D-3D alignments allow us to extract accurate derivative annotations such as dense pixel correspondences, depth and segmentation maps. We demonstrate the use of NAVI image collections on different problem settings and show that NAVI enables more thorough evaluations that were not possible with existing datasets. We believe NAVI is beneficial for systematic research progress on 3D reconstruction and correspondence estimation. Project page: https://navidataset.github.io

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 52 of its 73 references that are in the map. First posted on arXiv 15 Jun 2023.

Builds on

52 of 73 references.

References · 52

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  8. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  10. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  11. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  12. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
38 more
  1. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  2. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  3. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  4. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  5. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  6. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  7. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  8. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  9. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  10. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  11. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  12. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  13. 2022Kubric: A scalable dataset generatorcited by 373
  14. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  15. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  16. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  17. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  18. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  19. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 231
  20. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 224
  21. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 219
  22. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  23. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 204
  24. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  25. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  26. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  27. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  28. 2018Scan2CAD: Learning CAD Model Alignment in RGB-D Scanscited by 142
  29. 2019SPair-71k: A Large-scale Benchmark for Semantic Correspondencecited by 140
  30. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  31. 2016Deep Image Homography Estimationcited by 135
  32. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  33. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  34. 2020Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrievecited by 65
  35. 2022LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discoverycited by 65
  36. 2020CoReNet: Coherent 3D scene reconstruction from a single RGB imagecited by 45
  37. 20183D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Imagecited by 40
  38. 2023ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collectionscited by 22

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 20; 2025: 13; 2026: 17.

53 papers.

Sort:

By area:

  1. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 175
  2. 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 95
  3. 2024RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Modelscited by 88
  4. 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 55
  5. 2024TIPS: Text-Image Pretraining with Spatial awarenesscited by 37
  6. 2024MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priorscited by 28
  7. 2024SPA: 3D Spatial-Awareness Enables Effective Embodied Representationcited by 28
  8. 2025LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Modelscited by 23
  9. 2025E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-trainingcited by 20
  10. 2024SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wildcited by 18
  11. 2024Customizing Text-to-Image Diffusion with Object Viewpoint Controlcited by 13
  12. 2024Toward a Holistic Evaluation of Robustness in CLIP Modelscited by 13
38 more
  1. 2024Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuningcited by 13
  2. 2024Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variationcited by 13
  3. 2024MVImgNet2.0: A Larger-scale Dataset of Multi-view Imagescited by 12
  4. 2025UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedbackcited by 12
  5. 2026TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignmentcited by 12
  6. 2023PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environmentscited by 11
  7. 2024Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesiscited by 9
  8. 2026MV-S2V: Multi-View Subject-Consistent Video Generationcited by 9
  9. 2023ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Modelscited by 8
  10. 2025CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Modelscited by 8
  11. 2026MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoningcited by 8
  12. 2023Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Imagescited by 7
  13. 2024Probing the Mid-level Vision Capabilities of Self-Supervised Learningcited by 7
  14. 2024Can Generative Video Models Help Pose Estimation?cited by 7
  15. 2026Efficient Universal Perception Encodercited by 6
  16. 2026Stream3D: Sequential Multi-View 3D Generation via Evidential Memorycited by 6
  17. 2024GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Modelscited by 5
  18. 2025Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillationcited by 5
  19. 2024Extreme Two-View Geometry From Object Poses with Diffusion Modelscited by 4
  20. 2025MuM: Multi-View Masked Image Modeling for 3D Visioncited by 4
  21. 2026A Mixed Diet Makes DINO An Omnivorous Vision Encodercited by 3
  22. 2025GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedracited by 2
  23. 2025Muskie: Multi-view Masked Image Modeling for 3D Vision Pre-trainingcited by 2
  24. 2025Multi-View Foundation Modelscited by 2
  25. 2025MatSpray: Fusing 2D Material World Knowledge on 3D Geometrycited by 2
  26. 2026Revisiting Multi-Task Visual Representation Learningcited by 2
  27. 20243D Congealing: 3D-Aware Image Alignment in the Wildcited by 1
  28. 2024Generalizable Single-view Object Pose Estimation by Two-side Generating and Matchingcited by 1
  29. 2025PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesiscited by 1
  30. 2026VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimizationcited by 1
  31. 20263D-IDE: 3D Implicit Depth Emergentcited by 1
  32. 2024OpenMaterial: A Large-scale Dataset of Complex Materials for 3D Reconstructioncited by 0
  33. 2025Another BRIXEL in the Wall: Towards Cheaper Dense Featurescited by 0
  34. 2026SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Modelscited by 0
  35. 2026SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Modelscited by 0
  36. 2026ViT-Up: Faithful Feature Upsampling for Vision Transformerscited by 0
  37. 2026Mask-supervised Object-centric Representation Learning with LeJEPAcited by 0
  38. 2026DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Modelscited by 0

50 most cited of 53 All 53 (JSON)