← All conferences

CVPR 2022 Accepted Papers

The full list of 2,043 papers accepted at CVPR 2022 (IEEE/CVF Conference on Computer Vision and Pattern Recognition). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

Poster: 1,704Oral: 339
  1. How Much Does Input Data Type Impact Final Face Model Accuracy?Oral5 citations
  2. Joint Forecasting of Panoptic Segmentations With Difference AttentionOral5 citations
  3. Learning Object Context for Novel-View Scene Layout GenerationPoster5 citations
  4. Long-Term Visual Map Sparsification With Heterogeneous GNNPoster5 citations
  5. Point Cloud Color ConstancyPoster5 citations
  6. Primitive3D: 3D Object Dataset Synthesis From Randomly Assembled PrimitivesPoster5 citations
  7. Relative Pose From a Calibrated and an Uncalibrated Smartphone ImagePoster5 citations
  8. Searching the Deployable Convolution Neural Networks for GPUsPoster5 citations
  9. Sparse Non-Local CRFPoster5 citations
  10. TO-FLOW: Efficient Continuous Normalizing Flows With Temporal Optimization Adjoint With Moving SpeedPoster5 citations
  11. Weakly but Deeply Supervised Occlusion-Reasoned Parametric Road LayoutsPoster5 citations
  12. A Unified Model for Line Projections in Catadioptric Cameras With Rotationally Symmetric MirrorsPoster4 citations
  13. Cluster-Guided Image Synthesis With Unconditional ModelsPoster4 citations
  14. Convolution of Convolution: Let Kernels Spatially CollaboratePoster4 citations
  15. Enhancing Classifier Conservativeness and Robustness by PolynomialityOral4 citations
  16. Gaussian Process Modeling of Approximate Inference Errors for Variational AutoencodersPoster4 citations
  17. Learning Robust Image-Based Rendering on Sparse Scene Geometry via Depth CompletionPoster4 citations
  18. Learning To Zoom Inside Camera Imaging PipelinePoster4 citations
  19. Multi-Marginal Contrastive Learning for Multi-Label Subcellular Protein LocalizationPoster4 citations
  20. Multimodal Colored Point Cloud to Image AlignmentPoster4 citations
  21. Neural Recognition of Dashed Curves With Gestalt Law of ContinuityPoster4 citations
  22. RendNet: Unified 2D/3D Recognizer With Latent Space RenderingOral4 citations
  23. Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography AngiographyPoster4 citations
  24. Self-Supervised Spatial Reasoning on Multi-View Line DrawingsPoster4 citations
  25. Uniform Subdivision of Omnidirectional Camera Space for Efficient Spherical Stereo MatchingPoster4 citations
  26. FAM: Visual Explanations for the Feature Representations From Deep Convolutional NetworksPoster3 citations
  27. Learning To Restore 3D Face From In-the-Wild Degraded ImagesPoster3 citations
  28. Maximum Consensus by Weighted Influences of Monotone Boolean FunctionsPoster3 citations
  29. Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape LaplacianPoster3 citations
  30. Understanding Uncertainty Maps in Vision With Statistical TestingPoster3 citations
  31. AIM: An Auto-Augmenter for Images and MeshesPoster2 citations
  32. AxIoU: An Axiomatically Justified Measure for Video Moment RetrievalPoster2 citations
  33. Implicit Feature Decoupling With Depthwise QuantizationPoster2 citations
  34. Improving Video Model Transfer With Dynamic Representation LearningPoster2 citations
  35. Learning ABCs: Approximate Bijective Correspondence for Isolating Factors of Variation With Weak SupervisionOral2 citations
  36. Robust Combination of Distributed Gradients Under Adversarial PerturbationsPoster2 citations
  37. SoftCollage: A Differentiable Probabilistic Tree Generator for Image CollagePoster2 citations
  38. Symmetry-Aware Neural Architecture for Embodied Visual ExplorationPoster2 citations
  39. Weakly-Supervised Metric Learning With Cross-Module Communications for the Classification of Anterior Chamber Angle ImagesPoster2 citations
  40. YouMVOS: An Actor-Centric Multi-Shot Video Object Segmentation DatasetPoster2 citations
  41. CellTypeGraph: A New Geometric Computer Vision BenchmarkPoster1 citations
  42. Merry Go Round: Rotate a Frame and Fool a DNNPoster1 citations
  43. Using 3D Topological Connectivity for Ghost Particle Reduction in Flow ReconstructionPoster1 citations

Looking for submission deadlines instead? See the conference deadline calendar.