AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Efficient Camera Pose Augmentation for View Generalization in Robotic Policy Learning

Sen Wang, Huaiyi Dong, Jingyi Tian, lijiayi lijiayi, Zhuo Yang, Tongtong Cao, Anlin Chen, Shuang Wu, Sanping Zhou, Le Wang

ECCV 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
add GenSplat-rendered novel views to trainingDiffusion Policy · Real-world 6 tasks, Large perturbationsuccess rate: 27.78% -> 43.33%Improved
add GenSplat-rendered novel views to trainingpi0 · Real-world 6 tasks, Large perturbationsuccess rate: +13.3% relativeImproved
add GenSplat augmentation, unperturbed source viewspi0 and Diffusion Policy · Real-world, source (no perturbation)success rateNo clear effect
augment with diffusion-based VISTA viewspi0 · Real-world 6 tasks, Large perturbationavg success: 48.9 -> 37.8Hurt
augment with NoPoSplat viewspi0 · Real-world 6 tasks, Large perturbationavg success: 48.9 -> 36.7Hurt
use GenSplat instead of AnySplat viewspi0 · Real-world 6 tasks, Large perturbationavg success: 56.1 -> 62.2Improved
replace VGGT with permutation-equivariant architecture (ablation)GenSplat · Large (30deg, 6cm)policy success: 66.0 -> 70.0Improved
add 3D-prior distillation (ablation)GenSplat · Extreme (60deg, 12cm)policy success: 40.0 -> 46.0Improved
add 3D-prior distillation (ablation)GenSplat · novel view synthesisLPIPS: 5.03 -> 3.72Improved
increase generated views from 0 to 1 per demo (ablation)Diffusion Policy · Stack Block, Large perturbationsuccess rate: 30.0 -> 48.0Improved
increase generated views from 3 to 4 per demo (ablation)Diffusion Policy · Stack Block, Large perturbationsuccess rate: 64.0 -> 62.0No clear effect
increase generated views from 3 to 4 per demo (ablation)Diffusion Policy · Stack Cups, Large perturbationsuccess rate: 56.0 -> 54.0No 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