AI Paper Atlas

Research map / 3D vision / Depth and stereo

Extreme Structure From Motion for Indoor Panoramas Without Visual Overlaps

Mohammad Amin Shabani, Weilian Song, Makoto Odamaki, Hirochika Fujiki, Yasutaka Furukawa

ICCV 2021 · 3D vision › Depth and stereo · approach: Camera model and calibration for SfM · 17 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 ground-truth room shape, room type and door/window instead of predictions (ablation)Ours · Extreme indoor SfM, mAP K=1-5, delta=0.2 mmean average precision: 30.0 -> 50.4Improved
use ground-truth room shape, room type and door/window instead of predictions (ablation)Ours · Extreme indoor SfM, mAP K=1-5, delta=1.0 mmean average precision: 67.8 -> 70.9Improved
add room-type information (ablation)Ours · Extreme indoor SfM, mAP K=1-5, delta=0.2 mmean average precision: 21.3 -> 30.0Improved
add room-type information (ablation)Ours · Extreme indoor SfM, mAP K=1-5, delta=0.6 mmean average precision: 60.0 -> 59.6No clear effect
add room-type information (ablation)Ours · Extreme indoor SfM, mAP K=1-5, delta=1.0 mmean average precision: 64.3 -> 67.8Improved
add door/window information (ablation)Ours · Extreme indoor SfM, mAP K=1-5, delta=0.6 mmean average precision: 26.5 -> 59.6Improved
add door/window information (ablation)Ours · Extreme indoor SfM, mAP K=1-5, delta=1.0 mmean average precision: 34.7 -> 67.8Improved
add room-type and door/window information (ablation)Ours · Extreme indoor SfM, mAP K=1-5, delta=0.2 mmean average precision: 4.7 -> 30.0Improved
consider top-5 reconstructions instead of top-1Ours · Extreme indoor SfM, error <1.0 msuccess rate (%): 47 -> 78Improved
fine-tune HorizonNet on own layout annotationsHorizonNet · Room layout on own dataset3D IoU: 74.42 -> 88.12Improved
use room-to-room connections to define the relational graph instead of fully connected (ablation)ConvMPN · Extreme indoor SfMsuccess rateNo clear effect

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