SplatR : Experience Goal Visual Rearrangement with 3D Gaussian Splatting and Dense Feature Matching
This addresses a foundational challenge in Embodied AI for agents to rearrange scenes accurately, though it appears incremental by combining existing techniques.
The paper tackles the Experience Goal Visual Rearrangement task in Embodied AI by using 3D Gaussian Splatting for scene representation and dense feature matching with foundation model features, achieving improvements over state-of-the-art methods on the AI2-THOR benchmark.
Experience Goal Visual Rearrangement task stands as a foundational challenge within Embodied AI, requiring an agent to construct a robust world model that accurately captures the goal state. The agent uses this world model to restore a shuffled scene to its original configuration, making an accurate representation of the world essential for successfully completing the task. In this work, we present a novel framework that leverages on 3D Gaussian Splatting as a 3D scene representation for experience goal visual rearrangement task. Recent advances in volumetric scene representation like 3D Gaussian Splatting, offer fast rendering of high quality and photo-realistic novel views. Our approach enables the agent to have consistent views of the current and the goal setting of the rearrangement task, which enables the agent to directly compare the goal state and the shuffled state of the world in image space. To compare these views, we propose to use a dense feature matching method with visual features extracted from a foundation model, leveraging its advantages of a more universal feature representation, which facilitates robustness, and generalization. We validate our approach on the AI2-THOR rearrangement challenge benchmark and demonstrate improvements over the current state of the art methods