Computer Vision - ECCV 2026

DRS-VPT: Directly Re-localizing in Scenes using a Vision and Point Transformer.- Geometry Grounding: Elevating Blind Distortion Correction with 3D Structural Priors.- MTVDiff: Multimodal Conditional Latent Diffusion for Enhanced Thermal-to-Visible Face Translation.- OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams.- Infinite Gaze Generation for Videos with Autoregressive Diffusion.- SCORE: SubDistribution-aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-Identification.- OBBSeg: Irregular Lesion Segmentation under Oriented Bounding Box Annotations.- Evaluating and Understanding Model Editing for Medical Vision Language Models.- SAFE-Pruner: Semantic Attention–Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation.- TR-MoE: Temporal Reliability-Aware Mixture-of-Experts for Robust Tracking.- SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model.- Semantic Line Diffusion: Character-Consistent Line Art from text-annotated Storyboards.- From Local Geometry to Global Pseudo-Labeling for Robust Positive–Unlabeled Learning under Covariate Shift.- Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction.- Rethinking Adversary in Semantic Segmentation: An Out-of-Distribution Perspective.- UHD-MFF: Shattering Barriers in Multi-Focus Ultra-High-Definition Image Fusion via Learnable Lookup Tables.- ProAct: Agentic Lookahead in Interactive Environments.- Bottom-up modeling of repeated elements via single image analysis-by-synthesis.- Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation.- BWAFDA: Block-wise Weighted Attention Fusion with Detail-aware for No-Reference Image Quality Assessment.- MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing.- EgoPHI: Estimating 3D Hand-Object Contact and Force from Egocentric Vision.- Rectified Embedding Flow Learning for Aerial Multi-view  Geo-localization.- SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving.- GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editing.- IC-World: In-Context Generation for Shared World Modeling.- VERITAS: A Multi-agent Co-scientist for Verifiable Image-Derived Hypothesis Testing.- ROSE: Real-Time Open-World Scene Understanding from Monocular Video via Compact Multimodal 4D Scene Graphs.- FlashBEV: Fast and Memory-Efficient Exact BEV Transformation with IO-Awareness.- Bootstrapping Articulated 3D Reconstruction from 2D Image Collections.- ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs.- HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding.- Synthetic Sub-Aperture Phase Augmentation for Demosaicing 2×2 Shared Microlens Sensors.- Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth.- Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories.- DTI: Dynamic Trajectory Initialization for Generative Face Video Super-Resolution.- FreeGen: Feed-Forward Reconstruction–Generation Co-Training for Free-Viewpoint Driving Scene Synthesis.

• Erscheinungsdatum: 10.09.2026
• Autor/Autorin: Paolo Favaro
• Format: E-Book
• Dateiformat: PDF
• Kopierschutz: Wasserzeichen
• Dateigröße: 138.2 MB
• Verlag: SPRINGER
• Sprache: Englisch
• Umfang: 703 Seiten
• ISBN: 9783032373625
• Lieferung: Sofort per Download
• Hinweis: Sofort per Download lieferbar. Kein physischer Versand.
• Kompatibilität: Lesbar auf Geräten und Apps mit PDF-Unterstützung.