AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Audio-Visual Floorplan Reconstruction

Senthil Purushwalkam, Sebastià Vicenc Amengual Garí, Vamsi Krishna Ithapu, Carl Schissler, Philip Robinson, Abhinav Gupta, Kristen Grauman

ICCV 2021 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 39 citations (OpenAlex)

Read the paper

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 audio (device-generated) to RGB-only (ablation)AV-Map · Interior map, 4 steps, 40m2AP: 69.05 -> 73.67Improved
add audio (device-generated) to RGB-only (ablation)AV-Map · Interior map, 4 steps, 40m2Accuracy: 64.20 -> 66.51Improved
add audio (device-generated) to RGB-only (ablation)AV-Map · Interior map, 4 steps, 40m2Edge AP: 52.93 -> 55.21Improved
add RGB to audio-only (ablation)AV-Map · Interior map, 4 steps, 40m2AP: 70.44 -> 73.67Improved
add RGB to audio-only (Env. All Room) (ablation)AV-Map · Interior map, environment-generated All RoomAP: 65.42 -> 71.38Improved
add environment-generated audio (Env. Telephone) to RGB-only (ablation)AV-Map · Interior map, 4 stepsAP: 69.05 -> 72.30Improved
use environment-generated All Room audio instead of device-generated chirpAV-Map · Interior map, 4 stepsAP: 73.67 -> 71.38Hurt
train on sequences (t_V=4) instead of single steps (t_V=1) (ablation)AV-Map · Interior map, dev-generated audioAP: 68.91 -> 73.61Improved
train on sequences (t_V=4) instead of single steps (t_V=1) (ablation)AV-Map · Interior map, dev-generated audioAccuracy: 62.46 -> 66.51Improved
add audio to RGB-only at 16 steps with 164m2 area (ablation)AV-Map · Interior map AP, 164m2AP: 76.00 -> 80.71Improved
use AV-Map RGB-only variant versus OccAnt (no audio)AV-Map RGB-only · Interior map, 4 stepsAP: 60.27 -> 69.05Improved

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