mlsanityData to 7 Oct 2026

Cross-View Completion Models are Zero-shot Correspondence Estimators

arXiv 2412.09072 ↗First posted 12 Dec 2024cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

In this work, we explore new perspectives on cross-view completion learning by drawing an analogy to self-supervised correspondence learning. Through our analysis, we demonstrate that the cross-attention map within cross-view completion models captures correspondence more effectively than other correlations derived from encoder or decoder features. We verify the effectiveness of the cross-attention map by evaluating on both zero-shot matching and learning-based geometric matching and multi-frame depth estimation. Project page is available at https://cvlab-kaist.github.io/ZeroCo/.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 85 of its 106 references that are in the map. First posted on arXiv 12 Dec 2024.

Builds on

85 of 106 references.

References · 85

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  11. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  12. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
38 more
  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  3. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  4. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  5. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  6. 2023Vision Transformers Need Registerscited by 844
  7. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  8. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  9. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  10. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  11. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  12. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  13. 2023Emergent Correspondence from Image Diffusioncited by 437
  14. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  15. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  16. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 324
  17. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 297
  18. 2023RoMa: Robust Dense Feature Matchingcited by 296
  19. 2022MultiMAE: Multi-modal Multi-task Masked Autoencoderscited by 287
  20. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  21. 2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 215
  22. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  23. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  24. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 175
  25. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
  26. 2018Neighbourhood Consensus Networkscited by 173
  27. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  28. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 169
  29. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 165
  30. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  31. 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
  32. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  33. 2019SelFlow: Self-Supervised Learning of Optical Flowcited by 128
  34. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  35. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  36. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  37. 2020EfficientPS: Efficient Panoptic Segmentationcited by 111
  38. 2016Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothnesscited by 101

50 most cited of 85 All 85 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 18; 2026: 12.

30 papers.

Sort:

By area:

  1. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 122
  2. 2025Easi3R: Estimating Disentangled Motion from DUSt3R Without Trainingcited by 88
  3. 2025Visual Representation Alignment for Multimodal Large Language Modelscited by 40
  4. 2025Emergent Temporal Correspondences from Video Diffusion Transformerscited by 30
  5. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  6. 2025Emergent Outlier View Rejection in Visual Geometry Grounded Transformerscited by 19
  7. 2025C3G: Learning Compact 3D Representations with 2K Gaussianscited by 18
  8. 20253D Scene Prompting for Scene-Consistent Camera-Controllable Video Generationcited by 13
  9. 2025Towards Cross-View Point Correspondence in Vision-Language Modelscited by 12
  10. 2025Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regressioncited by 10
  11. 2025D2USt3R: Enhancing 3D Reconstruction for Dynamic Scenescited by 10
  12. 2025CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Modelscited by 8
18 more
  1. 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
  2. 2025S^4M: Boosting Semi-Supervised Instance Segmentation with SAMcited by 5
  3. 20253D-Aware Vision-Language Models Fine-Tuning with Geometric Distillationcited by 4
  4. 2025MuM: Multi-View Masked Image Modeling for 3D Visioncited by 4
  5. 2026UFO-4D: Unposed Feedforward 4D Reconstruction from Two Imagescited by 4
  6. 2026TORA: Topological Representation Alignment for 3D Shape Assemblycited by 4
  7. 2026Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Modelscited by 3
  8. 2025Muskie: Multi-view Masked Image Modeling for 3D Vision Pre-trainingcited by 2
  9. 2025Unique Lives, Shared World: Learning from Single-Life Videoscited by 2
  10. 2026No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videoscited by 2
  11. 2026Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstructioncited by 2
  12. 2026CORAL: Correspondence Alignment for Improved Virtual Try-Oncited by 1
  13. 2026Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparisoncited by 1
  14. 2026Lookalike3D: Seeing Double in 3Dcited by 0
  15. 2026Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstructioncited by 0
  16. 2026PROSE: Training-Free Egocentric Scene Registration with Vision-Language Modelscited by 0
  17. 2026RoMa-Omega: What Feed-Forward 3D Models Know About Image Matchingcited by 0
  18. 2026Emergent Multi-View Geometry Through Self-Distillationcited by 0