AI Paper Atlas

Research map / 3D vision / Depth and stereo

Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image

Jerred Chen, Ronald Clark

ICCV 2025 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 1 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
estimate velocity from a single blurred image instead of multi-image MASt3Rsingle-image blur method · Real-world test sequences (avg of 4)rotational velocity RMSE w_x (rad/s): 4.04 -> 1.22Improved
estimate velocity from a single blurred image instead of multi-image MASt3Rsingle-image blur method · Real-world test sequences (avg of 4)translational velocity RMSE v_x (m/s): 1.60 -> 1.11Improved
compare with second-best method on rotational velocitysingle-image blur method · Real-world test sequencesrotational velocity RMSE: 31% reductionImproved
compare with second-best method on translational velocitysingle-image blur method · Real-world test sequencestranslational velocity RMSE: 24% reductionImproved
compare with zero-velocity prior on translation zsingle-image blur method · Real-world test sequences (avg of 4)translational velocity RMSE v_z (m/s): 1.24 -> 0.92Improved
COLMAP on blurred sequencesCOLMAP · Real-world test sequencespose reconstructionHurt
single-image network instead of DROID-SLAM for runtimesingle-image blur method · Real-world test sequencesaverage FPS: 4.34 -> 30.17Improved
use direct velocity prediction instead of IMU preintegrationsingle-image blur method · long videovelocity drift: drift after 20 secondsImproved
MASt3R beats ours on dining sequence translationMASt3R · dining sequencetranslational velocity RMSE v_x (m/s): 0.82 vs 0.95Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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