{"ID":2873846,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.06191","arxiv_id":"2509.06191","title":"Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)","abstract":"Recent 3D generative models, which are capable of generating full object shapes from just a few images, now open up new opportunities in robotics. In this work, we show that 3D generative models can be used to augment a dataset from a single real-world demonstration, after which an omnidirectional policy can be learned within this imagined dataset. We found that this enables a robot to perform a task when initialised from states very far from those observed during the demonstration, including starting from the opposite side of the object relative to the real-world demonstration, significantly reducing the number of demonstrations required for policy learning. Through several real-world experiments across tasks such as grasping objects, opening a drawer, and placing trash into a bin, we study these omnidirectional policies by investigating the effect of various design choices on policy behaviour, and we show superior performance to recent baselines which use alternative methods for data augmentation.","short_abstract":"Recent 3D generative models, which are capable of generating full object shapes from just a few images, now open up new opportunities in robotics. In this work, we show that 3D generative models can be used to augment a dataset from a single real-world demonstration, after which an omnidirectional policy can be learned...","url_abs":"https://arxiv.org/abs/2509.06191","url_pdf":"https://arxiv.org/pdf/2509.06191v1","authors":"[\"Yifei Ren\",\"Edward Johns\"]","published":"2025-09-07T20:00:59Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false}