AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation

Xiaoming Zhao, Harsh Agrawal, Dhruv Batra, Alexander G. Schwing

ICCV 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents · 42 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 depth to RGB input for VO (RGB-D vs RGB-only) (ablation)VO model · Gibson-4+ val (noisy, no GPS+Compass)success rate: 52 -> 61 (Row 1 vs Row 3)Improved
add RGB to depth-only VO input (ablation)VO model · Gibson-4+ val (noisy, no GPS+Compass)success rate: 54 -> 61Improved
add Dropout to last two layers of VO (ablation)VO RGB-D · Gibson-4+ val (noisy, no GPS+Compass)success rate: 61 -> 68 (success +7, SPL +5)Improved
replace single forward pass with 10 stochastic Dropout test-time passes (ablation)VO RGB-D + Dropout · Gibson-4+ val (noisy, no GPS+Compass)success rate: 68 -> 42Hurt
use separate per-action models (SepAct) instead of single model (ablation)VO RGB-D + Dropout · Gibson-4+ val (noisy, no GPS+Compass)success rate: 68 -> 75Improved
use 3x wider unified model instead of SepAct (ablation)VO RGB-D + Dropout · Gibson-4+ val (noisy, no GPS+Compass)success rate: 75 -> 70 (SPL 56 -> 52)Hurt
expose unified model to action via embedding instead of SepAct (ablation)VO RGB-D + Dropout · Gibson-4+ val (noisy, no GPS+Compass)success rate: 75 -> 72 (success and SPL both drop 3 points)Hurt
add geometric invariance losses (ablation)VO SepAct · Gibson-4+ val (noisy, no GPS+Compass)success rate: 75 -> 77 (SPL 56 -> 57)Improved
add data augmentation by reversing turn pairs only (ablation)VO SepAct · Gibson-4+ val (noisy, no GPS+Compass)success rate: 75 -> 75No clear effect
add depth discretization with 10 channels (ablation)VO SepAct+GeoInv · Gibson-4+ val (noisy, no GPS+Compass)success rate: 77 -> 79 (SPL 57 -> 60)Improved
use 5 instead of 10 depth discretization channels (ablation)VO full · Gibson-4+ val (noisy, no GPS+Compass)success rate: 79 -> 74Hurt
use 20 instead of 10 depth discretization channels (ablation)VO full · Gibson-4+ val (noisy, no GPS+Compass)success rate: 79 -> 79No clear effect

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