AI Paper Atlas

Research map / 3D vision / 3D generation

Structured 4D Latent Predictive Model for Robot Planning

Zhiyi Li, Peilin Wu, Xiaoshen Han, Ruojin Cai, Yilun Du

ICML 2026 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 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
use decoded point clouds instead of voxels as inverse-dynamics input (ablation)Structured 4D latent model · StackCube, 4 viewssuccess rate: closed-loop 73% -> 84%; open-loop 57% -> 57%Improved
use decoded point clouds instead of 3D latents as inverse-dynamics input (ablation)Structured 4D latent model · StackCube, 4 viewssuccess rate: closed-loop 80% -> 84%; open-loop 66% -> 57%No clear effect
use closed-loop replanning instead of open-loop with 4 training views (ablation)Structured 4D latent model · StackCubesuccess rate: 57% -> 84%Improved
increase training camera views from 4 to 40 (ablation)Structured 4D latent model · StackCubeChamfer distance: 7.10 -> 6.81Improved
increase training camera views from 4 to 40 (ablation)Structured 4D latent model · StackCubeplanning success rate (open-loop): 57% -> 84%Improved
increase training views from 4 to 40 (ablation)Structured 4D latent model · StackCubecPSNR: 28.89 -> 26.75Hurt
replace video generative planners with 4D latent predictive modelStructured 4D latent model · ManiSkill3 averagesuccess rate: 24.7% -> 61.3%Improved
replace TesserAct with structured 4D latentsStructured 4D latent model · RLBench averagesuccess rate: 61.7% -> 75.3%Improved
use 3D predictive rollout instead of DP3 under visual perturbation (noise)Structured 4D latent model · StackCube zero-shotsuccess rate: 47% -> 80%Improved
use predictive rollout instead of 3D Diffuser Actor at noise 0.10Ours-CL · StackCube zero-shotsuccess rate: 7% -> 86%Improved
use 4D latent model instead of Wan-2.1 for generationStructured 4D latent model · 4D generationChamfer distance: 43.09 -> 5.95Improved
use 4D latent model instead of TesserAct for image qualityStructured 4D latent model · 4D generationSSIM: 0.86 -> 0.79Hurt

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