AI Paper Atlas

Research map / 3D vision / Depth and stereo

AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration

Javier Tirado-Garín, Javier Civera

ICCV 2025 · 3D vision › Depth and stereo · approach: Camera model and calibration for SfM · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use FoV fields as target instead of rays with cosine loss (ablation)AnyCalib_pinhole · Averaged perspective benchmarksRE: 26.05 -> 23.81Improved
use FoV fields instead of DSINE-style angular ray loss (ablation)AnyCalib_pinhole · Averaged perspective benchmarksRE: 24.95 -> 23.81Improved
use light DPT decoder without transposed convolutions (ablation)AnyCalib_pinhole · Averaged perspective benchmarksMACs: 243.2G -> 187.8GImproved
light DPT decoder instead of original (ablation)AnyCalib_pinhole · Averaged perspective benchmarksRE: 24.99 -> 23.81Improved
extend OpenPano with 4055 unconstrained panoramas (ablation)AnyCalib_pinhole · Averaged perspective benchmarksRE: 26.62 -> 23.81Improved
fit intrinsics with RANSAC minimal samples instead of non-minimal closed form (ablation)AnyCalib on Kannala-Brandt · ScanNet++RE: 20.61 -> 1019Hurt
train AnyCalib on general projections versus perspective-only for perspective imagesAnyCalib_gen vs AnyCalib_pinhole · Stanford2D3DvFoV error (deg): 2.55 -> 2.95Mixed
swap camera model at runtime (radial, KB, UCM) without retrainingAnyCalib · Distorted imagesAE (deg)No clear effect
compare AnyCalib with 3D foundation model MoGe on perspective imagesAnyCalib_pinhole · TartanAirvFoV error (deg): 1.61 -> 3.62Hurt
apply AnyCalib to edited (stretched/cropped) images versus DiffCalibAnyCalib · TartanAir (edited)e_f (relative focal error): 0.62 -> 0.19Improved

Later papers that compared with this method

1 later accepted paper reports AnyCalib as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy