We utilize 3DGS serves as a persistent spatial memory for embodied navigation, enabling the agent to ‘‘hallucinate’’ optimal views for high-fidelity Vision-Language Model (VLM) reasoning.
We utilize 3DGS serves as a persistent spatial memory for embodied navigation, enabling the agent to ‘‘hallucinate’’ optimal views for high-fidelity Vision-Language Model (VLM) reasoning.
we propose Splat2BEV, a Gaussian Splatting-assisted BEV perception framework that aims to learn BEV feature representations that are both semantically rich and geometrically precise.
We propose Segment then Splat, an Open-vocabulary 3D segmentation method that reverses the long established approach of “segmentation after reconstruction” by dividing Gaussians into distinct object sets before reconstruction.
We propose Noise Guided Splatting, a method that handles the inherit “false transparency” artifact in 3DGS by injecting opaque noise Gaussians in the object volume during training, the object surfaces are encourages surface Gaussians to adopt higher opacity.