LIBERO-Occ: 視点想像によるシーン起因の遮蔽下での視覚言語行動モデルの評価と改善
LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imagination
遮蔽がある操作環境でVLAモデルの性能が低下する問題を調べ、遮蔽評価ベンチマークLIBERO-Occを導入し、補完視点を想像して行動予測に活用する手法VIMを提案した。
著者: Taishan Li, Jiwen Zhang, Siyuan Wang, Xuanjing Huang, Zhongyu Wei
分類: cs.CV, cs.AI
原文アブストラクト
Vision-Language-Action (VLA) models achieve strong performance on standard manipulation benchmarks, but most evaluations assume that task-relevant objects are fully visible. This assumption often fails in realistic settings, where occlusion makes manipulation partially observable. In this paper, we study \textit{scene-induced occlusion} as a fundamental challenge for VLA models and introduce \textbf{LIBERO-Occ}, an occlusion-oriented extension of LIBERO. Experiments show that state-of-the-art VLAs suffer substantial performance degradation under occlusion. To address this issue, we propose \textbf{Viewpoint Imagination (VIM)}, which generates a complementary view from an occluded primary observation and conditions action prediction on both observed and imagined evidence. VIM improves robustness across task suites, occlusion types, and severity levels without requiring additional cameras at deployment time, suggesting that viewpoint imagination is an promising mechanism for perception completion in partially observable manipulation. Our benchmark and corresponding code are available at: \href{https://github.com/litsh/Libero-Occ}{https://github.com/litsh/Libero-Occ}.