9 papers
Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation
Ali Zia, Muhammad Umer Ramzan, Abdelwahed Khamis +2
Radar sensors provide reliable perception under adverse weather and lighting conditions, but their sparse, noisy, and weakly semantic measurements make dense semantic segmentation…
Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation
Ali Zia, Usman Ali, Abdul Rehman +5
Test-time adaptation (TTA) has emerged as a promising paradigm for mitigating distribution shifts in deep models. However, existing TTA approaches for anomaly segmentation remain l…
Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection
Ali Zia, Usman Ali, Muhammad Umer Ramzan +3
Training-free video anomaly detection (VAD) has recently emerged as a scalable alternative to supervised approaches, yet existing methods largely rely on static prompting and geome…
Component-Aware Sketch-to-Image Generation Using Self-Attention Encoding and Coordinate-Preserving Fusion
Ali Zia, Muhammad Umer Ramzan, Usman Ali +3
Translating freehand sketches into photorealistic images remains a fundamental challenge in image synthesis, particularly due to the abstract, sparse, and stylistically diverse nat…
Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chaining
Ali Zia, Usman Ali, Umer Ramzan +3
Deep topological data analysis (TDA) offers a principled framework for capturing structural invariants such as connectivity and cycles that persist across scales, making it a natur…
2D_3D Feature Fusion via Cross-Modal Latent Synthesis and Attention Guided Restoration for Industrial Anomaly Detection
Usman Ali, Ali Zia, Abdul Rehman +5
Industrial anomaly detection (IAD) increasingly benefits from integrating 2D and 3D data, but robust cross-modal fusion remains challenging. We propose a novel unsupervised framewo…