collaborators

8 papers

cs.CV2026

PT-WNO: Point Transformer with Wavelet Neural Operator for 3D Point Cloud Semantic Segmentation

Nhut Le, Maryam Rahnemoonfar

Point cloud semantic segmentation requires architectures that capture both fine-grained local geometry and broad global scene structure. Transformer-based networks have demonstrate…

cs.LG2026

OPTNet: Ordering Point Transformer Network for Post-disaster 3D Semantic Segmentation

Nhut Le, Ehsan Karimi, Maryam Rahnemoonfar

Post-disaster damage assessment requires rapid and accurate semantic segmentation of 3D point clouds to identify critical infrastructure such as damaged buildings and roads. Early…

cs.CV2026

Instruct-ICL: Instruction-Guided In-Context Learning for Post-Disaster Damage Assessment

Armin Zarbaft, Ehsan Karimi, Nhut Le +1

Rapid and accurate situational awareness is essential for effective response during natural disasters, where delays in analysis can significantly hinder decision-making. Training t…

cs.CV2026

DA-SegFormer: Damage-Aware Semantic Segmentation for Fine-Grained Disaster Assessment

Kevin Zhu, William Tang, Raphael Hay Tene +3

Rapid and accurate damage assessment following natural disasters is critical for effective emergency response. However, identifying fine-grained damage levels (e.g., distinguishing…

cs.CV2026

Geometric Flood Depth Estimation: Fusing Transformer-Based Segmentation with Digital Elevation Models

Nhut Le, Ehsan Karimi, Maryam Rahnemoonfar

Post-disaster situational awareness relies heavily on understanding both the extent and the volume of floodwaters. While 2D semantic segmentation provides accurate flood masking, i…

cs.CV2025

3D Semantic Segmentation for Post-Disaster Assessment

Nhut Le, Maryam Rahnemoonfar

The increasing frequency of natural disasters poses severe threats to human lives and leads to substantial economic losses. While 3D semantic segmentation is crucial for post-disas…