Skip to page content
SAVRN
Search Plan a project

Open-weight model

camera-error-metric

by HyunsungKim kimhosoo/camera-error-metric

camera-error-metric is an open-weight model from HyunsungKim. Its published files total 35.5 KB.

Files (keep this directory layout -- scripts resolve imports via the parent dir): For each clip, DA3 (Depth-Anything-3) is run once over the full 77-frame GT video and once over the model's output.mp4, giving one W2C extrinsic per frame per side.

Parameters—
Context—
Weights35.5 KB
License—
AccessOpen weights
Monthly Downloads—

Model Card

Files (keep this directory layout -- scripts resolve imports via the parent dir): For each clip, DA3 (Depth-Anything-3) is run once over the full 77-frame GT video and once over the model's output.mp4, giving one W2C extrinsic per frame per side. Trajectories are made first-frame-relative and translation-normalized, then RotErr / TransErr / CamMC are computed (calcroterr, calctranserr, calccammc in evalcamerada3.py; math adapted from SWMbench). Per-model result = mean over clips (and per split Real/Syn). - Python env with torch, opencv-python, numpy, Pillow - depthanything3 package (Depth-Anything-3) and the checkpoint depth-anything/DA3NESTED-GIANT-LARGE-1.1 (auto-downloaded from the HF…

Excerpt from the card by HyunsungKim.

Identity and Version

Repository
kimhosoo/camera-error-metric
Publisher
HyunsungKim
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
3d6352eba518fcb70556e522a83c987870bc0cd4
First published
2026-09-21
Last updated
2026-09-21

Files and Weights

3 files, 35.5 KB in total.

Documentation1 file · 3.0 KB
Other1 file · 31.0 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
README.mdDocumentation3.0 KB —
camera_error_metric.tar.gzOther31.0 KB b3f785fea7b6
.gitattributesRepository1.5 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download from HyunsungKim

Released by HyunsungKim through its official repository on Hugging Face.