Computer Vision – ECCV 2022 : 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXIII / 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 ; 13693

Language:

English

Subjects (All):

Computer vision.

Computer Vision.

Local Subjects:

Computer Vision.

Physical Description:

1 online resource (804 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:

SimpleRecon: 3D Reconstruction without 3D Convolutions

Structure and Motion from Casual Videos

What Matters for 3D Scene Flow Network

Correspondence Reweighted Translation Averaging

Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

Objects Can Move: 3D Change Detection by Geometric Transformation Consistency

Language-Grounded Indoor 3D Semantic Segmentation in the Wild

Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs

Deforming Radiance Fields with Cages

FLEX: Extrinsic Parameters-Free Multi-View 3D Human Motion Reconstruction

MODE: Multi-View Omnidirectional Depth Estimation with 360° Cameras

GigaDepth: Learning Depth from Structured Light with Branching Neural Networks

ActiveNeRF: Learning Where to See with Uncertainty Estimation

PoserNet: Refining Relative Camera Poses Exploiting Object Detections

Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation

Unbiased Gradient Estimation for Differentiable Surface Splatting via Poisson Sampling

Towards Learning Neural Representations from Shadows

Class-Incremental Novel Class Discovery

Unknown-Oriented Learning for Open Set Domain Adaptation

Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

Class-Agnostic Object Counting Robust to Intraclass Diversity

Burn after Reading: Online Adaptation for Cross-Domain Streaming Data

Mind the Gap in Distilling StyleGANs

Improving Test-Time Adaptation via Shift-Agnostic Weight Regularization and Nearest Source Prototypes

Learning Instance-Specific Adaptation for Cross-Domain Segmentation

RegionCL: Exploring Contrastive Region Pairsfor Self-Supervised Representation Learning

Long-Tailed Class Incremental Learning

DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning

Adversarial Partial Domain Adaptation by Cycle Inconsistency

Combating Label Distribution Shift for Active Domain Adaptation

GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation

CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation

A Unified Framework for Domain Adaptive Pose Estimation

A Broad Study of Pre-training for Domain Generalization and Adaptation

Prior Knowledge Guided Unsupervised Domain Adaptation

GCISG: Guided Causal Invariant Learning for Improved Syn-to-Real Generalization

AcroFOD: An Adaptive Method for Cross-Domain Few-Shot Object Detection

Unsupervised Domain Adaptation for One-Stage Object Detector Using Offsets to Bounding Box

Visual Prompt Tuning

Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap.

Other Format:

Print version: Avidan, Shai Computer Vision - ECCV 2022

ISBN:

9783031198274

3031198271