[Submitted on 30 Oct 2026 (v1), last revised 4 Nov 2026 (this version, v2)]
Abstract:Egocentric observations provide a robot-centric view of manipulation processes, capturing contact interactions and object-state changes that are important for visuomotor policy learning but difficult to observe from external cameras. However, collecting such data at scale remains expensive due to additional hardware requirements and platform-specific deployment costs. Synthesizing egocentric observations from large-scale exocentric manipulation videos provides a scalable alternative. However, existing methods struggle to synthesize physically consistent and policy-relevant egocentric videos under substantial viewpoint transformations, severe occlusions, complex object interactions, and inherently sparse observations from available exocentric this http URL will be made publicly available at this https URL
Submission history
From: Hao Xue [view email]
[v1] Fri, 30 Oct 2026 14:50:06 UTC (8,534 KB)
[v2] Wed, 4 Nov 2026 15:38:24 UTC (6,099 KB)
