Full Description
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 23-27, 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.
Contents
StyleGAN-Human.A Data-Centric Odyssey of Human Generation.- ColorFormer. Image Colorization via Color Memory Assisted Hybrid-Attention Transformer.- EAGAN. Efficient Two-Stage Evolutionary Architecture Search for GANs.- Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation.- DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation.- Multimodal Conditional Image Synthesis with Product-of-Experts GANs.- Auto-Regressive Image Synthesis with Integrated Quantization.- JoJoGAN. One Shot Face Stylization.- VecGAN: Image-to-Image Translation with Interpretable Latent Directions.- Any-Resolution Training for High-Resolution Image Synthesis.- CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer.- CANF-VC: Conditional Augmented Normalizing Flows for Video Compression.- Bi-Level Feature Alignment for Versatile Image Translation and Manipulation.- High-Fidelity Image Inpainting with GAN Inversion.- DeltaGAN: Towards Diverse Few-Shot Image Generation with Sample-Specific Delta.- Image Inpainting with Cascaded Modulation GAN and Object-Aware Training.- StyleFace: Towards Identity-Disentangled Face Generation on Megapixels.- Video Extrapolation in Space and Time.- Contrastive Learning for Diverse Disentangled Foreground Generation.- BIPS.Bi-modal Indoor Panorama Synthesis via Residual Depth-Aided Adversarial Learning.- Augmentation of rPPG Benchmark Datasets: Learning to Remove and Embed rPPG Signals via Double Cycle Consistent Learning from Unpaired Facial Videos.- Geometry-Aware Single-Image Full-Body Human Relighting.- 3D-Aware Indoor Scene Synthesis with Depth Priors.- Deep Portrait Delighting.- Vector Quantized Image-to-Image Translation.- The Surprisingly Straightforward Scene Text Removal Method with Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis.- Free-Viewpoint RGB-D Human Performance Capture and Rendering.- Multiview Regenerative Morphing with Dual Flows.- Hallucinating Pose-Compatible Scenes.- Motion and Appearance Adaptation for Cross-Domain Motion Transfer.- Layered Controllable Video Generation.- Custom Structure Preservation in Face Aging.- Spatio-Temporal Deformable Attention Network for Video Deblurring.- NeuMesh: Learning Disentangled Neural Mesh-Based Implicit Field for Geometry and Texture Editing.- NeRF for Outdoor Scene Relighting.- CoGS: Controllable Generation and Search from Sketch and Style.- HairNet: Hairstyle Transfer with Pose Changes.- Unbiased Multi-Modality Guidance for Image Inpainting.- Intelli-Paint: Towards Developing More Human-Intelligible Painting Agents.- Motion Transformer for Unsupervised Image Animation.- NUWA: Visual Synthesis Pre-training for Neural visUal World creAtion.- EleGANt: Exquisite and Locally Editable GAN forMakeup Transfer.
