AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Towards Physically Executable 3D Gaussian for Embodied Navigation

Bingchen Miao, Rong Wei, Zhiqi Ge, Xiaoquan sun, Shiqi Gao, Jingzhe Zhu, Renhan Wang, Siliang Tang, Jun Xiao, Rui Tang, Juncheng Li

ICLR 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views

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 NaVILA-base on 500k SAGE-Bench trajectory-instruction pairs (3DGS data)NaVILA · VLN-CE R2R Val-UnseenSR: 0.29 -> 0.38Improved
fine-tune NaVid-base on SAGE-Bench dataNaVid · VLN-CE R2R Val-UnseenSR: 0.22 -> 0.31Improved
fine-tune NaVILA-base on SAGE-Bench dataNaVILA · SAGE-Bench VLN (high-level)SR: 0.21 -> 0.46Improved
fine-tune NaVid-base on SAGE-Bench dataNaVid · SAGE-Bench VLN (high-level)SR: 0.10 -> 0.36Improved
use 3DGS-Mesh hybrid environment instead of scanned mesh (ablation)NaVILA-base · rendering speedrender time per frame (ms): 16.7 -> 6.2Improved
use 3DGS data instead of scanned mesh for training (ablation)NaVILA-base · training convergencetime to SR=40% (hrs): 4.8 -> 6.2Hurt
increase number of training scenes at fixed sample size vs increase samples (ablation)SAGE-trained VLN model · VLN-CE val-unseenperformanceImproved
increase sampling density at a fixed number of scenes (800) (ablation)SAGE-trained VLN model · VLN-CE val-unseenperformanceImproved
fine-tune NaVILA on SAGE data (continuity trade-off)NaVILA-SAGE · SAGE-Bench VLNICP and PS vs original NaVILA: original NaVILA ICP 0.61, PS 0.68; NaVILA-SAGE ICP 0.54, PS 0.74Mixed
low-level vs high-level instructionsNaVILA · SAGE-Bench VLNSR: 0.56 -> 0.39Hurt
longer trajectories and higher scene complexityVLN models · SAGE-Bench slicesSRHurt

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