AI Paper Atlas

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

VMLoc: Variational Fusion For Learning-Based Multimodal Camera Localization

Kaichen Zhou, Changhao Chen, Bing Wang, Muhamad Risqi U. Saputra, Niki Trigoni, Andrew Markham

AAAI 2021 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 19 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
fuse RGB and depth with variational PoE, attention, and importance weightingcamera localization · 7-Scenes averageposition error: 0.20 m -> 0.19mImproved
fuse RGB and depth with variational PoE, attention, and importance weightingcamera localization · 7-Scenes averageorientation error: 7.56^{\circ} -> 7.01^{\circ}Improved
fuse RGB and lidar-derived depth with variational PoE, attention, and importance weightingcamera localization · Oxford RobotCar averageposition error: 23.8 m -> 17.5mImproved
fuse RGB and lidar-derived depth with variational PoE, attention, and importance weightingcamera localization · Oxford RobotCar averageorientation error: 8.19^{\circ} -> 4.92^{\circ}Improved
add depth input to the RGB-only VMLoc (ablation)VMLoc · Oxford RobotCar averageposition error: 23.9 m -> 17.5mImproved
add depth input to the RGB-only VMLoc (ablation)VMLoc · Oxford RobotCar averageorientation error: 7.22^{\circ} -> 4.92^{\circ}Improved
replace attention-based feature concatenation with PoE fusion and importance weighting (ablation)VMLoc · Oxford RobotCar averageposition error: 19.3 m -> 17.5mImproved
replace attention-based feature concatenation with PoE fusion and importance weighting (ablation)VMLoc · Oxford RobotCar averageorientation error: 5.35^{\circ} -> 4.92^{\circ}Improved
add importance weighting and the proposed unbiased objective to MVAE-based PoE fusion (ablation)VMLoc · Oxford RobotCar averageposition error: 18.7 m -> 17.5mImproved
add importance weighting and the proposed unbiased objective to MVAE-based PoE fusion (ablation)VMLoc · Oxford RobotCar averageorientation error: 5.16^{\circ} -> 4.92^{\circ}Improved
use full VMLoc rather than the ablated fusion variants (ablation)camera localization · Oxford RobotCar, RGB corruption lvl=1position error: 229.1 m; 235.5m; 241.9mMixed
use full VMLoc rather than the ablated fusion variants (ablation)camera localization · Oxford RobotCar, RGB corruption lvl=2position error: 484.7 m; 478.0 m; 464.7mImproved

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