Michael Ramamonjisoa

monocular depth estimation (2) image reconstruction (2) self-supervised learning (2) vision-language alignment (1) depth estimation (1) boundary detection (1) zero-shot classification (1) open-vocabulary semantic segmentation (1) monocular vision (1) encoder-decoder architecture (1) wavelet decomposition (1) zero-shot semantic segmentation (1) clip vision-language model (1) unsupervised object localization (1) multi-scale approach (1) monocular depth prediction (1) depth reconstruction (1) depth map prediction (1) occlusion boundary detection (1) displacement field (1)