most citedSoftNeuro: Fast Deep Inference using Multi-platform Optimization

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

PureCLIP-Depth: Prompt-Free and Decoder-Free Monocular Depth Estimation within CLIP Embedding Space

Ryutaro Miya, Kazuyoshi Fushinobu, Tatsuya Kawaguchi

We propose PureCLIP-Depth, a completely prompt-free, decoder-free Monocular Depth Estimation (MDE) model that operates entirely within the Contrastive Language-Image Pre-training (…