AI Paper Atlas

Research map / 3D vision / 3D generation

SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation

Hao Shi, Bin Xie, Yingfei Liu, Yang Yue, Tiancai Wang, Haoqiang Fan, Xiangyu Zhang, Gao Huang

AAAI 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 5 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
decouple semantics and geometry (ablation)RVT-2-style baseline · RLBench 18 tasks, heavy noiseaverage success rate (%): 57.0 -> 68.7Improved
decouple semantics and geometry (ablation)RVT-2-style baseline · RLBench 18 tasks, no noiseaverage success rate (%): 81.4 -> 85.1Improved
add Semantic-guided Geometric Module (SGM) (ablation)decoupled model · RLBench 18 tasks, heavy noiseaverage success rate (%): 68.7 -> 73.9Improved
add Semantic-guided Geometric Module (SGM) (ablation)decoupled model · RLBench 18 tasks, no noiseaverage success rate (%): 85.1 -> 86.4Improved
add Spatial Transformer (SPT) (ablation)decoupled model with SGM · RLBench 18 tasks, heavy noiseaverage success rate (%): 73.9 -> 76.4Improved
add Spatial Transformer (SPT) (ablation)decoupled model with SGM · RLBench 18 tasks, no noiseaverage success rate (%): 86.4 -> 87.4Improved
use SpatialActor instead of RVT-2 under heavy depth noiseRVT-2 · RLBench heavy noiseaverage success rate (%): 57.0 -> 76.4Improved
use SpatialActor instead of RVT-2 for few-shot adaptationRVT-2 · RLBench few-shot (19 novel tasks, 10 demos)average success rate (%): 46.9 -> 79.2Improved
use SpatialActor instead of RVT-2 on high-precision tasksRVT-2 · RLBench Insert Pegsuccess rate (%): 40.0 -> 93.3Improved
use SpatialActor instead of RVT-2 on Close Jar and Open DrawerRVT-2 · RLBench (18 tasks, 249 variations)success rate (%): Close Jar 100.0 -> 94.0; Open Drawer 74.0 -> 82.0Mixed
use SpatialActor instead of RVT-2 in real-world Stack Cup and Stack BlockRVT-2 · Real-worldsuccess rate (%): Stack Cup 30% -> 30%; Stack Block 40% -> 35%No clear effect

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