Eccv 2026 Refracgs

Summary

Title: HitMem: Hierarchical Temporal 3D Memory with Multi-Modal Context-Aware Retrieval for Dynamic Environments Abstract: ... Diffusion to Obfuscation: Time-Adaptive Synthesized Generation Against Gradient Leakage Attacks in Federated Learning. Paper: RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models. Video for paper: VLA Knows Its Limits. Project link: hatchetproject.github.io/autohorizon/ Continuous 6-DoF pose estimation is essential for autonomous UAV operations. Yet, existing visual odometry and SLAM methods ... OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning. Title: ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views Authors: Giuseppe Stracquadanio, Kevin Raj ... Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors. This video presents the paper "FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact ... Our work, “Scaling Multi-Reference Image Generation with Dynamic Reward Optimization,” has been accepted to