Computer Vision - ECCV 2026

TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects.- What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features.- Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment.- Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models.- GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding.- HippoCamp: Benchmarking Contextual Agents on Personal Computers.- TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation.- DA-F2F: Domain-Adaptive Object Detection with Feature-to-Feature Modulation and Alignment.- Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning.- RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios.- LIIFusion: Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation.- DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming.- A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world.- PACO: Stabilizing Vision Embeddings along Local Paths for Robust Vision-Language Models.- DocLayout-VL: A Foundational Model for Hierarchical, Open-set, and Promptable Document Layout Segmentation.- MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources.- ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching.- RePer-360: Releasing Perspective Priors for 360° Depth Estimation via Self-Modulation.- Steerable Vision Transformers.- Single-Query Person-Centric Bimanual Hand-Object Interaction Detection.- SkyLume: A Large-Scale Multi-Illumination Aerial Benchmark for Urban Scene Reconstruction and Beyond.- Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention.- CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection.- DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing.- Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation.- ESC: Emotional Self-Correction for Reliable Vision-Language Models.- VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors.- CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts.- PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation.- CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization.- BiCE-HG: A Bi-Conditional Egocentric Hand Gesture Dataset for Intelligent Reality Systems.- Ceptor: Vision-Language Model-Infused Diverse Guidance for Detecting Anything.- PointSplat: Compact Gaussian Splatting via Human-Centric Prediction.- SFKD: Spatial–Frequency Joint-Aware Heterogeneous Knowledge Distillation via Multi-Level Wavelet Spectral Interaction.- Extending a Large View Synthesis Model for Multi-view Panoptic Segmentation.- PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving.

• Erscheinungsdatum: 11.09.2026
• Autor/Autorin: Paolo Favaro
• Format: E-Book
• Dateiformat: PDF
• Kopierschutz: Wasserzeichen
• Dateigröße: 165.5 MB
• Verlag: SPRINGER
• Sprache: Englisch
• Umfang: 691 Seiten
• ISBN: 9783032370167
• Lieferung: Sofort per Download
• Hinweis: Sofort per Download lieferbar. Kein physischer Versand.
• Kompatibilität: Lesbar auf Geräten und Apps mit PDF-Unterstützung.