FocsleFocsle
II

MiDaS-Distilled-S

2%
by Intel ISL

Distilled MiDaS small. Maintained reference for cross-vendor depth comparisons.

DepthMITINT8FP16monoculardepthreference
88K downloads 4.2K deploymentsUpdated Dec 18, 2027
Headline:22.4ms · Snapdragon 8 Gen 3 NPU · FP16

About this model

Distilled MiDaS small. Maintained reference for cross-vendor depth comparisons.

Authored by intel-isl. Curated into the Fo’c’sle reference set on 2027-12-18. All cross-chip benchmarks below were collected in matched-pair runs in the HIL lab using the same input pipeline, same upstream preprocessing, and the same downstream consumer. See the methodology page for the full protocol.

Task
Depth
Parameters
18.4 M
Benchmarked on
6 chips
Deployments
4.2K

Architecture

Encoder + DPT decoder
Inferred from upstream weights · simplified
ImageViT-S/16Hybrid stemConv stageDPT decoderRefinementDisparity

Headline benchmarks

Training data

Pretrained on the upstream maintainer’s released checkpoint. Edge-distillation pass uses 2.4M frames from the Fo’c’sle distillation corpus (consented public data + opt-in publisher contributions). Quantization-aware fine-tune uses 320K calibration samples drawn from the target task’s eval domain.

  • Pretraining corpus: upstream maintainer release
  • Distillation corpus: 2,400,000 frames
  • Calibration set: 320,000 samples (per task)
  • Eval set: standard benchmark + matched-pair HIL runs