AI Paper Atlas

Research map / 3D vision / 3D generation

Be Everywhere - Hear Everything (BEE): Audio Scene Reconstruction by Sparse Audio-Visual Samples

Mingfei Chen, Kun Su, Eli Shlizerman

ICCV 2023 · 3D vision › 3D generation · approach: Visual-acoustic scene modeling · 9 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 joint audio-visual rendering from sparse receivers instead of best prior learning method (APNet)BEE · Matterport3D unseen scenesSTFT error: 0.515 -> 0.438Improved
add Audio-Visual Spatial Encoder (ablation)BEE · Matterport3D unseen scenesENV: 0.512 -> 0.458Improved
add Spatial Enhanced Visual Representation (visual attention) (ablation)BEE · Matterport3D unseen scenesSTFT error: 0.454 -> 0.438Improved
add cross-attention and averaged integrated rendering over receivers (ablation)BEE · Matterport3D unseen scenesSTFT error: 0.509 -> 0.438Improved
add transposed-conv audio-visual branch (ablation)BEE · Matterport3D unseen scenesDPAM: 0.424 -> 0.348Improved
add MLP magnitude branch (ablation)BEE · Matterport3D unseen scenesSTFT error: 0.626 -> 0.438Improved
use BEE vs non-learning baselinesBEE · Replica and Matterport3DSTFT error: 3.456 -> 0.438 (Mean vs BEE, Matterport3D unseen)Improved
use BEE for human preferenceBEE · human subject studypreference votes (%): 29.6% / 26.4% -> 44%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