Computer Vision – ECCV 2022 : 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part III / edited by Shai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, Tal Hassner.

Format:

Book

Author/Creator:

Avidan, Shai, author.

Series:

Lecture Notes in Computer Science, 1611-3349 ; 13663

Language:

English

Subjects (All):

Computer vision.

Computer Vision.

Local Subjects:

Computer Vision.

Physical Description:

1 online resource (811 pages)

Edition:

1st ed. 2022.

Place of Publication:

Cham : Springer Nature Switzerland : Imprint: Springer, 2022.

Summary:

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:

TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement

LaTeRF: Label and Text Driven Object Radiance Fields

MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis

Unsupervised Deep Multi-Shape Matching

Texturify: Generating Textures on 3D Shape Surfaces

Autoregressive 3D Shape Generation via Canonical Mapping

PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees

UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation

PRIF: Primary Ray-Based Implicit Function

Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction

CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes

PlaneFormers: From Sparse View Planes to 3D Reconstruction

Learning Implicit Templates for Point-Based Clothed Human Modeling

Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks

Structure-Aware Editable Morphable Model for 3D Facial Detail Animation and Manipulation

MoFaNeRF: Morphable Facial Neural Radiance Field

PointInst3D: Segmenting 3D Instances by Points

Cross-Modal 3D Shape Generation and Manipulation

Latent Partition Implicit with Surface Codes for 3D Representation

Implicit Field Supervision for Robust Non-rigid Shape Matching

Learning Self-Prior for Mesh Denoising Using Dual Graph Convolutional Networks

diffConv: Analyzing Irregular Point Clouds with an Irregular View

PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

SeedFormer: Patch Seeds Based Point Cloud Completion with Upsample Transformer

DeepMend: Learning Occupancy Functions to Represent Shape for Repair

A Repulsive Force Unit for Garment Collision Handling in Neural Networks

Shape-Pose Disentanglement Using SE(3)-Equivariant Vector Neurons

3D Equivariant Graph Implicit Functions

PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation

3D Shape Sequence of Human Comparison and Classification Using Current and Varifolds

Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification

Unsupervised Pose-Aware Part Decomposition for Man-Made Articulated Objects

MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks

SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement

The Shape Part Slot Machine: Contact-Based Reasoning for Generating 3D Shapes from Parts

Spatiotemporal Self-Attention Modeling with Temporal Patch Shift for Action Recognition

Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning

Semi-Supervised Temporal Action Detection with Proposal-Free Masking

Zero-Shot Temporal Action Detection via Vision-Language Prompting

CycDA: Unsupervised Cycle Domain Adaptation to Learn from Image to Video

S2N: Suppression-Strengthen Network for Event-Based Recognition under Variant Illuminations

CMD: Self-Supervised 3D Action Representation Learning with Cross-Modal Mutual Distillation.

Other Format:

Print version: Avidan, Shai Computer Vision - ECCV 2022

ISBN:

9783031200625

3031200624