Blog

Blog sub title

GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and 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.

GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and 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.

Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian Splatting

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.

Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting
Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting

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.

Fix False Transparency by Noise Guided Splatting
Fix False Transparency by Noise Guided Splatting

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.

Latest Posts

GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and 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.

GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and 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.

Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian Splatting

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.