Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XV

ISBN-13: 9783031197833 / Angielski / Miękka / 2022 / 743 str.

Shai Avidan; Gabriel Brostow; Moustapha Cissé

Opis

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.

Spis treści

WaveGAN.Frequency-Aware GAN for High-Fidelity Few-Shot Image Generation.- End-to-End Visual Editing with a Generatively Pre-trained Artist.- High-Fidelity GAN Inversion with Padding Space.- Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping.- Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives.- Make-a-Scene: Scene-Based Text-to-Image Generation with Human Priors.- 3D-FM GAN: Towards 3D-Controllable Face Manipulation.- Multi-Curve Translator for High-Resolution Photorealistic Image Translation.- Deep Bayesian Video Frame Interpolation.- Cross Attention Based Style Distribution for Controllable Person Image Synthesis.- KeypointNeRF. Generalizing Image-Based Volumetric Avatars Using Relative Spatial Encoding of Keypoints.- ViewFormer: NeRF-Free Neural Rendering from Few Images Using Transformers.- L-Tracing. Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing.- A Perceptual Quality Metric for Video Frame Interpolation.- Adaptive Feature Interpolation for Low-Shot Image Generation.- PalGAN: Image Colorization with Palette Generative Adversarial Networks.- Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis.- Learning Prior Feature and Attention Enhanced Image Inpainting.- Temporal-MPI. Enabling Multi-Plane Images for Dynamic Scene Modelling via Temporal Basis Learning.- 3D-Aware Semantic-Guided Generative Model for Human Synthesis.- Temporally Consistent Semantic Video Editing.- Error Compensation Framework for Flow-Guided Video Inpainting.- Scraping Textures from Natural Images for Synthesis and Editing.- Single Stage Virtual Try-On via Deformable Attention Flows.- Improving GANs for Long-Tailed Data through Group Spectral Regularization.- Hierarchical Semantic Regularization of Latent Spaces in StyleGANs.- IntereStyle.Encoding an Interest Region for Robust StyleGAN Inversion.- StyleLight.HDR Panorama Generation for Lighting Estimation and Editing.- Contrastive Monotonic Pixel-Level Modulation.- Learning Cross-Video Neural Representations for High-Quality Frame Interpolation.- Learning Continuous Implicit Representation for Near-Periodic Patterns.- End-to-End Graph-Constrained Vectorized Floorplan Generation with Panoptic Refinement.- Few-Shot Image Generation with Mixup-Based Distance Learning.- A Style-Based GAN Encoder for High Fidelity Reconstruction of Images and Videos.- FakeCLR. Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs.- BlobGAN. Spatially Disentangled Scene Representations.- Unified Implicit Neural Stylization.- GAN with Multivariate Disentangling for Controllable Hair Editing.- Discovering Transferable Forensic Features for CNN-Generated Images Detection.- Harmonizer: Learning to Perform White-Box Image and Video Harmonization.- Text2LIVE.Text-Driven Layered Image and Video Editing.- Digging into Radiance Grid for Real-Time View Synthesis with Detail Preservation.