AI Paper Atlas

Research map / 3D vision / Face and shape

GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images

Jiahao Sun, Dingkun Wei, Zehong Shen, Hongyu Zhou, Yujun Shen, Liang Li

ECCV 2026 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 0 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 Gravity-View alignment (ablation)GARDEN (point cloud) · NVS ablation HypersimRMSE: 0.2961 -> 0.2751Improved
add Gravity-View alignment (ablation)GARDEN (point cloud, with simulation) · NVS ablation HypersimRMSE: 0.3002 -> 0.2751Improved
add Gravity-View alignment (ablation)GARDEN (3DGS) · NVS ablation HypersimRMSE: 0.3171 -> 0.2840Improved
add Gravity-View alignment (ablation)GARDEN (point cloud) · NVS ablation HypersimCompleteness: 0.0743 -> 0.0387Improved
add physically grounded integration beyond GV plus FoundationPose (ablation)GARDEN (point cloud) · NVS ablation HypersimRMSE: 0.2753 -> 0.2751Improved
factorize scene (objects plus background) instead of DA3 output (ablation)GARDEN (point cloud) · NVS ablation HypersimCompleteness: 0.0516 -> 0.0387Improved
factorize scene instead of DA3 output (ablation)GARDEN (point cloud) · NVS ablation HypersimAccuracy: 0.0082 -> 0.0658Hurt
factorize scene instead of DA3 output (ablation)GARDEN (3DGS) · NVS ablation HypersimRMSE: 0.3068 -> 0.2840Improved
replace CAD retrieval with gravity-aligned factorization (post-sim)GARDEN vs LiteReality · Object-centric material recoveryRMSE: 0.2163 -> 0.1880Improved
replace CAD retrieval with factorization (post-sim)GARDEN vs LiteReality · Object-centric material recoverySSIM: 0.4353 -> 0.4240No clear effect
replace CAD retrieval with factorization (post-sim)GARDEN vs LiteReality · Holistic sceneLPIPS: 0.6522 -> 0.4081Improved
evaluate static rather than post-simulationGARDEN (point cloud) · Holistic sceneRMSE: 0.1616 -> 0.1511Improved

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