ScenePilot: Plug-and-Play 3D Scene Repair across Generators
Abstract
Text-driven 3D scene generators have made substantial progress, yet their outputs often retain collisions, boundary violations, orientation errors, and structural inconsistencies. Existing correction mechanisms are typically coupled to generator-specific scene representations and execution pipelines, making repair difficult to reuse across heterogeneous systems. We introduce ScenePilot, a plug-and-play 3D scene repair policy designed to make corrective behavior transferable across generators. ScenePilot decouples repair reasoning from generator-specific execution through a canonical scene-editing interface, allowing one shared multimodal policy to operate across heterogeneous generators without modifying or retraining their underlying generation models. At inference time, ScenePilot performs conservative closed-loop repair: each round proposes at most one atomic edit, executes it tentatively, and retains the change only when a shared verifier confirms improvement. We further construct SceneReverse, which transforms clean 3D scenes into executable recovery trajectories and provides generator-independent supervision for learning atomic repair decisions. Combined with supervised learning and reward-guided policy optimization based on realized improvements, SceneReverse enables repair learning without relying on failure traces from any target generator. On SceneEval, the same frozen ScenePilot policy consistently improves scenes from five heterogeneous generators unseen during policy training, without backend-specific policy fine-tuning, using only lightweight backend adapters. These results support transferable 3D scene repair as a reusable capability that can be attached to existing generators through a canonical interface.
est. 32% chance this paper gets accepted at ICLR 2027.
What do you think this paper will get?
All positions stay anonymous.