AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation

Guanxing Lu, Shiyi Zhang, Ziwei Wang, Changliu Liu, Jiwen Lu, Yansong Tang

ECCV 2024 · 3D vision › Gaussian splatting · approach: Deformable 4D Gaussian splatting · 85 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 Gaussian regressor with geometry reconstruction loss (ablation)PerceiverIO manipulation policy · RLBench 10 tasksaverage success rate (%): 23.6 -> 39.2Improved
add semantic feature distillation from Stable Diffusion (ablation)ManiGaussian (geometry only) · RLBench 10 tasksaverage success rate (%): 39.2 -> 41.6Improved
add deformation predictor with future scene consistency loss (ablation)ManiGaussian (geometry only) · RLBench 10 tasksaverage success rate (%): 39.2 -> 43.6Improved
combine geometry, semantics and dynamics (ablation)PerceiverIO policy · RLBench 10 tasksaverage success rate (%): 23.6 -> 44.8Improved
add dynamics loss on top of geometry and semantics (ablation)ManiGaussian · RLBench Planning taskssuccess rate (%): 46.0 -> 40.0Hurt
add dynamics loss on top of geometry and semantics (ablation)ManiGaussian · RLBench Long taskssuccess rate (%): 8.0 -> 14.0Improved
increase semantic loss weight from 0.0001 to 0.001 (ablation)ManiGaussian (no dynamics) · RLBench 10 tasksaverage success rate (%): 41.6 -> 37.6Hurt
decrease semantic loss weight from 0.0001 to 0.00001 (ablation)ManiGaussian (no dynamics) · RLBench 10 tasksaverage success rate (%): 41.6 -> 35.2Hurt
use ManiGaussian instead of GNFactorGNFactor · RLBench 10 tasksaverage success rate (%): 31.7 -> 44.8Improved
use explicit Gaussian scene reconstruction instead of NeRFGNFactor · RLBench learning curvetraining speed: 2.29x faster training, 1.18x performanceImproved

Later papers that compared with this method

3 later accepted papers report ManiGaussian as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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