Tiny and Efficient Model for the Edge Detection Generalization
Paper โข 2308.06468 โข Published
TEED (Tiny and Efficient Edge Detector, 58 K parameters) by Xavier Soria Poma
et al., converted to ONNX for TerraGen. MIT, as upstream (LICENSE
is upstream's, unchanged).
checkpoints/BIPED/5/5_model.pth (upstream's default checkpoint) at
xavysp/TEED commit 40fa4b1391dc6424f88989d0ca75d5b592c8681d. The authors do not state what the
released weights were trained on beyond the BIPED checkpoint folder's name.image float32 [1, 3, H, W], BGR order, 0-255, with the mean (104.007, 116.669, 122.679)
subtracted; H and W multiples of 8.edges float32 [1, 1, H, W], edge probability 0-1 (sigmoid of TEED's fused output).Citation: Soria, Li, Rouhani, Sappa, "Tiny and Efficient Model for the Edge Detection Generalization", ICCV 2023 Workshops (arXiv:2308.06468).