AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Snap Angle Prediction for 360° Panoramas

Bo Xiong, Kristen Grauman

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning

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
add pixel-objectness foreground objective with learned snap angle prediction (vs Canonical view)snap angle model · 360 panoramas, allobject overlap IoU: 74.4% -> 81.1%Improved
add learned snap angles instead of random rotationsnap angle model · User study, allpreference rate: Prefer Ours 65.3% vs Random 22.4%Improved
add learned snap angles instead of canonical orientationsnap angle model · User study, allpreference rate: Prefer Ours 53.8% vs Canonical 31.5%Improved
add snap angles to cubemaps for memorabilitysnap angle model · Image memorability (all, normalized)normalized score: 46.8% -> 59.8%Improved
add snap angles to cubemaps for aestheticssnap angle model · Image aesthetics (all, normalized)normalized score: 44.3% -> 52.9%Improved
project panoramas with snap angles before feeding pretrained classifier (single face)ResNet-101 · Cubemap recognition, Singleaccuracy (%): 68.5 -> 70.1Improved
project panoramas with snap angles before feeding pretrained classifier (pano)ResNet-101 · Cubemap recognition, Panoaccuracy (%): 66.5 -> 68.1Improved
replace pixel objectness input with ground-truth foreground maps (T=4) (ablation)snap angle model · Foreground disruptionforeground disruption error: 0.283 -> 0.259Improved
increase search budget T from 2 to 10 with pixel objectness input (ablation)snap angle model · Foreground disruptionforeground disruption error: 0.305 -> 0.277Improved
increase search budget T from 2 to 10 with ground-truth input (ablation)snap angle model · Foreground disruptionforeground disruption error: 0.274 -> 0.234Improved
use learned content-based search instead of Uniform rotatesnap angle model · Foreground disruption vs budgetforeground disruption: up to 10% (absolute)Improved
use learned content-based search instead of Saliency baselinesnap angle model · Foreground disruption vs budgetforeground disruption: up to 31% (absolute)Improved

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