AI Paper Atlas

Research map / 3D vision / Gaussian splatting

EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device

Gunjan Chhablani, Xiaomeng Ye, Muhammad Zubair Irshad, Zsolt Kira

ICCV 2025 · 3D vision › Gaussian splatting · approach: Animatable Gaussian human avatars · 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
fine-tune on Polycam mesh of deployment sceneHM3D pre-trained policy · Real-world lounge ImageNavsuccess rate: 50% -> 70%Improved
fine-tune on DN mesh of deployment sceneHM3D pre-trained policy · Real-world lounge ImageNavsuccess rate: 50% -> 70%Improved
fine-tune on Polycam meshHSSD pre-trained policy · Real-world lounge ImageNavsuccess rate: 10% -> 50%Improved
fine-tune on DN meshHSSD pre-trained policy · Real-world lounge ImageNavsuccess rate: 10% -> 40%Improved
fine-tune 20M steps on scene meshHM3D pre-trained policy · Sim Captured/MuSHRoom scenessuccess rate: approaching 90%+Improved
fine-tune 20M steps on scene meshHM3D pre-trained policy · conf_c (DN mesh)success rate: 0.16 -> 0.84Improved
add HM3D/HSSD large-scale pre-training before scene training (ablation)policy · Real-world lounge ImageNav (DN mesh)success rate: 10% -> 70%Improved
add HM3D/HSSD pre-training before scene training (ablation)policy · Real-world lounge ImageNav (Polycam mesh)success rate: 50% -> 70%Improved
continue HM3D pre-training beyond ~400M steps (ablation)HM3D policy · Captured scenes zero-shotsuccess rateNo clear effect
continue HSSD pre-training beyond 300M steps (ablation)HSSD policy · Captured scenes zero-shotsuccess rateNo clear effect
use iPhone GT depth instead of monocular depth encoders (ablation)DN-Splatter · MuSHRoom meshesF-score: 0.688 -> 0.748Improved
use Metric3D-v2 normals instead of Omnidata (ablation)DN-Splatter · MuSHRoom meshesF-score: 0.748 -> 0.752Improved

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