CASWiT CASWiT is a context-aware Transformer for ultra-high resolution aerial image segmentation. CASWiT achieves SOTA performances on FLAIR-HUB and URUR. heig-vd-geo/CASWiT Image Segmentation • Updated 1 day ago • 5 Context-Aware Semantic Segmentation via Stage-Wise Attention Paper • 2601.11310 • Published 27 days ago
Context-Aware Semantic Segmentation via Stage-Wise Attention Paper • 2601.11310 • Published 27 days ago
GridNet-HD A new multimodal dataset "GridNet-HD" specifically designed for 3D semantic segmentation of electrical infrastructures. Running 2 GridNet HD Leaderboard 🥇 2 GridNet HD Leaderboard! heig-vd-geo/GridNet-HD Viewer • Updated 23 days ago • 800 • 3.48k • 14 GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructure Paper • 2601.13052 • Published 24 days ago heig-vd-geo/SPT_GridNet-HD_baseline Other • Updated 22 days ago • 3
GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructure Paper • 2601.13052 • Published 24 days ago
CASWiT CASWiT is a context-aware Transformer for ultra-high resolution aerial image segmentation. CASWiT achieves SOTA performances on FLAIR-HUB and URUR. heig-vd-geo/CASWiT Image Segmentation • Updated 1 day ago • 5 Context-Aware Semantic Segmentation via Stage-Wise Attention Paper • 2601.11310 • Published 27 days ago
Context-Aware Semantic Segmentation via Stage-Wise Attention Paper • 2601.11310 • Published 27 days ago
GridNet-HD A new multimodal dataset "GridNet-HD" specifically designed for 3D semantic segmentation of electrical infrastructures. Running 2 GridNet HD Leaderboard 🥇 2 GridNet HD Leaderboard! heig-vd-geo/GridNet-HD Viewer • Updated 23 days ago • 800 • 3.48k • 14 GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructure Paper • 2601.13052 • Published 24 days ago heig-vd-geo/SPT_GridNet-HD_baseline Other • Updated 22 days ago • 3
GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructure Paper • 2601.13052 • Published 24 days ago