AI Paper Atlas

Research map / 3D vision / 3D generation

Neural Multisensory Scene Inference

Jae Hyun Lim, Pedro O O. Pinheiro, Negar Rostamzadeh, Chris Pal, Sungjin Ahn

NeurIPS 2019 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 2 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 APoE instead of the summed-context C-GQN baselineGMN · MESE cross-modal density estimation: HAPTIC→GRAY, HAPTIC→RGB, and RGB→HAPTICconditional log-likelihoodImproved
Use APoE instead of the summed-context C-GQN baselineGMN · MESE scene classification from image, haptic, or combined contextsclassification accuracyImproved
Use APoE instead of the summed-context C-GQN baselineGMN · MESE, unseen context modality configurationsnegative ELBOImproved
Use APoE rather than separate full ConvDraw networks for each expertMultisensory inference network · MESE, 5 modalitiesparameters: 53M -> 29MImproved
Use APoE rather than separate full ConvDraw networks for each expertMultisensory inference network · MESE, 14 modalitiesparameters: 131M -> 51MImproved
Use APoE rather than separate full ConvDraw networks for each expertMultisensory inference network · MESE, 5 modalitiestime per iteration: 790 ms -> 679 msImproved
Use APoE rather than separate full ConvDraw networks for each expertMultisensory inference network · MESE, 14 modalitiestime per iteration: 2059 ms -> 1189 msImproved
Use APoE rather than the summed-context C-GQN baselineMultisensory inference network · MESE, 2 modalitiestime per iteration: 346 -> 587Hurt
Use APoE rather than the summed-context C-GQN baselineMultisensory inference network · MESE, 5 modalitiestime per iteration: 397 -> 679Hurt
Use APoE rather than the summed-context C-GQN baselineMultisensory inference network · MESE, 8 modalitiestime per iteration: 481 -> 992Hurt
Use APoE rather than the summed-context C-GQN baselineMultisensory inference network · MESE, 14 modalitiestime per iteration: 866 -> 1189Hurt
Aggregate additional haptic context observationsGMN · MESE cross-modal generationprediction qualityImproved

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