AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI

Xinhao Liu, Jiaqi Li, Youming Deng, Ruxin Chen, Yingjia Zhang, Yifei Ma, Li Guo, Yiming Li, Jing Zhang, Chen Feng

CVPR 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 4 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
build simulation from LIV-SLAM geometry (poses + LiDAR init) instead of vision-only reconstruction3DGS · Wanderland NVS (interpolated views)PSNR: 18.27 -> 20.37Improved
build simulation from LIV-SLAM geometry instead of COLMAP3DGS · Wanderland NVS (extrapolated views)PSNR: 17.00 -> 17.92Improved
LIV-SLAM geometry vs Vid2Sim on extrapolated LPIPSWanderland · Wanderland NVS (extrapolated views)LPIPS: 0.371 vs 0.445Hurt
RL post-training in Vid2Sim-built environmentCityWalker · Wanderland test splitSR: SR -21%Hurt
RL post-training in Wanderland geometrically grounded environmentCityWalker · Wanderland test splitSR: SR +14%Improved
RL post-training in Wanderland environmentNoMaD · Wanderland test splitSR: SR +8%Improved
RL post-training in Vid2Sim environmentNoMaD · Wanderland test splitSR: SR 0.24 (0%)No clear effect
evaluate in Vid2Sim environments instead of Wanderlandnavigation policies · Wanderland test splitSRHurt
use best vision-only method vs LIV-SLAM posesCOLMAP / feed-forward 3D models · Wanderland pose estimationT-ATE scaled (m): 30 cm / 5 deg best-of-all errorHurt
outdoor vs indoor scenesnavigation models · Wanderland benchmarkSR: NaVILA 0.47 -> 0.31Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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