The 39-volume set, comprising the LNCS books 13661 until 13699, constitutes the refereed proceedings of the 17th European Conference on Computer Vision, ECCV 2022, held in Tel Aviv, Israel, during October 2327, 2022.
The 1645 papers presented in these proceedings were carefully reviewed and selected from a total of 5804 submissions. The papers deal with topics such as computer vision; machine learning; deep neural networks; reinforcement learning; object recognition; image classification; image processing; object detection; semantic segmentation; human pose estimation; 3d reconstruction; stereo vision; computational photography; neural networks; image coding; image reconstruction; object recognition; motion estimation.
Inhalt Editing Out-of-Domain GAN Inversion via Differential Activations.- On the Robustness of Quality Measures for GANs.- Sound-Guided Semantic Video Generation.- Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation.- Controllable Video Generation through Global and Local Motion Dynamics.- StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN.- Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer.- Combining Internal and External Constraints for Unrolling Shutter in Videos.- WISE: Whitebox Image Stylization by Example-Based Learning.- Neural Radiance Transfer Fields for Relightable Novel-View Synthesis with Global Illumination.- Transformers As Meta-Learners for Implicit Neural Representations.- Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment.- High-Resolution Virtual Try-On with Misalignment and OcclusionHandled Conditions.- A Codec Information Assisted Framework for Efficient Compressed Video Super-Resolution.- Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis.- AdaNeRF: Adaptive Sampling for Real-Time Rendering of Neural Radiance Fields.- Improving the Perceptual Quality of 2D Animation Interpolation.- Selective TransHDR: Transformer-Based Selective HDR Imaging Using Ghost Region Mask.- Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution.- GeoAug: Data Augmentation for Few-Shot NeRF with Geometry Constraints.- DoodleFormer: Creative Sketch Drawing with Transformers.- Implicit Neural Representations for Variable Length Human Motion Generation.- Learning Object Placement via Dual-Path Graph Completion.- Expanded Adaptive Scaling Normalization for End to End Image Compression.- Generator Knows What Discriminator Should Learn in Unconditional GANs.- Compositional Visual Generation with Composable Diffusion Models.- ManiFest: Manifold Deformation for Few-Shot Image Translation.- ManiFest: Manifold Deformation for Few-Shot Image Translation.- Supervised Attribute Information Removal and Reconstruction for Image Manipulation.- BLT: Bidirectional Layout Transformer for Controllable Layout Generation.- Diverse Generation from a Single Video Made Possible.- Rayleigh EigenDirections (REDs): Nonlinear GAN Latent Space Traversals for Multidimensional Features.- Bridging the Domain Gap towards Generalization in Automatic Colorization.- Generating Natural Images with Direct Patch Distributions Matching.- Context-Consistent Semantic Image Editing with Style-Preserved Modulation.- Eliminating Gradient Conflict in Reference-Based Line-Art Colorization.- Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations.- JPEG Artifacts Removal via Contrastive Representation Learning.- Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning.- Efficient Long-Range Attention Network for Image Super-Resolution.- FlowFormer: A Transformer Architecture for Optical Flow.- Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction.- Learning Shadow Correspondence for Video Shadow Detection.- Metric Learning Based Interactive Modulation for Real-World Super-Resolution.
Computer Vision ECCV 2022
17th European Conference, Tel Aviv, Israel, October 23 27, 2022, Proceedings, Part XVII