AI Paper Atlas

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

Modality-Invariant Visual Odometry for Embodied Vision

Marius Memmel, Roman Bachmann, Amir Zamir

CVPR 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 10 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
Add explicit modality-invariance training to RGB-D VOT (ablation)VOT-B RGB-D on Gibson-4+ validation · Gibson-4+ validationsuccess: 88.2 -> 92.6Improved
Train with modality-invariance so Depth can be dropped at test time (ablation)RGB-D VOT · Gibson-4+ validation, Depth droppedsuccess: 26.1 -> 60.9Improved
Train with modality-invariance so RGB can be dropped at test time (ablation)RGB-D VOT · Gibson-4+ validation, RGB droppedsuccess: 75.9 -> 91.0Improved
Use Depth rather than RGB as the sole input modality (ablation)VOT on Gibson-4+ validation · Gibson-4+ validationsuccess: 59.3 -> 93.3Improved
Add multi-modal pre-training to RGB-D VOT without an action prior (ablation)VOT-B on Gibson-4+ validation · Gibson-4+ validationsuccess: 47.3 -> 85.7Improved
Add an action prior to pre-trained RGB-D VOT (ablation)VOT-B on Gibson-4+ validation · Gibson-4+ validationsuccess: 85.7 -> 88.2Improved
Add an action prior to pre-trained RGB VOT (ablation)VOT-B on Gibson-4+ validation · Gibson-4+ validationsuccess: 54.5 -> 59.3Improved
Add an action prior to pre-trained Depth VOT (ablation)VOT-B on Gibson-4+ validation · Gibson-4+ validationsuccess: 83.2 -> 93.3Improved
Use RGB-D instead of Depth-only with pre-training and an action prior (ablation)VOT-B on Gibson-4+ validation · Gibson-4+ validationsuccess: 93.3 -> 88.2Hurt
Add RGB observations to Depth-only VOT (ablation)VOT with modality-invariance training · Gibson-4+ validationsuccess: 93.3 -> 92.6Hurt
Train VOT using only RGB rather than Depth (ablation)VOT on Gibson-4+ validation · Gibson-4+ validationsuccess: 93.3 -> 59.3Hurt
Replace the proposed approach with Zhao et al.'s unified baselinePointGoal navigation on Gibson-4+ validation · Gibson-4+ validationsuccess: 92.6 -> 64.5Hurt

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