AI Paper Atlas

Research map / 3D vision / Depth and stereo

View Birdification in the Crowd: Ground-Plane Localization from Perceived Movements

Mai Nishimura, Shohei Nobuhara, Ko Nishino

IJCV 2023 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 5 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 view birdification instead of plain Social Force extrapolationSocial Force · Hotelabsolute pedestrian error: 0.289 -> 0.052Improved
use view birdification instead of plain Social Force extrapolationSocial Force · ETHabsolute pedestrian error: 0.261 -> 0.079Improved
use view birdification instead of plain Social Force extrapolationSocial Force · Studentsabsolute pedestrian error: 0.222 -> 0.010Improved
use view birdification instead of ConstVel extrapolationConstVel · Shibuya01absolute pedestrian error: 0.221 -> 0.024Improved
use Social Force instead of constant velocity interaction model in VBVB · ETHabsolute pedestrian error: 0.115 -> 0.079Improved
use Social Force instead of constant velocity interaction model in VBVB · Studentsabsolute pedestrian error: 0.023 -> 0.010Improved
use Social Force instead of constant velocity interaction model in VBVB · Hotelabsolute pedestrian error: 0.070 -> 0.052Improved
increase height variance sigma_h from 0.00 to 0.07 (ablation)VB-SF · Hotelabsolute pedestrian error: 0.052 -> 0.052No clear effect
replace manual centerlines with MOT detectionsVB · GTAVabsolute pedestrian error: 0.491 -> 0.530Hurt
replace manual centerlines with MOT detectionsVB · GTAVcamera translation error: 0.097 -> 0.101Hurt
select only nearby pedestrians in super-dense crowd (ablation)VB-SF · Shibuya01absolute pedestrian error: 0.023No clear effect
use nearby dynamic pedestrians instead of static keypoints beyond 6 mVB vs five-point solver · GTAV simulationcamera translation error: 0.50 -> 0.097Improved

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