SAGE: Semantic-Driven Adaptive Gaussian Splatting in Extended Reality
3D Gaussian Splatting (3DGS) has significantly improved the efficiency and realism of three-dimensional scene visualization in several applications, ranging from robotics to eXtended Reality (XR). This work presents SAGE (Semantic-Driven Adaptive Gaussian Splatting in Extended Reality), a novel framework designed to enhance the user experience by dynamically adapting the Level of Detail (LOD) of different 3DGS objects identified via a semantic segmentation. Experimental results demonstrate how SAGE effectively reduces memory and computational overhead while keeping a desired target visual quality, thus providing a powerful optimization for interactive XR applications.
Code (0)
등록된 구현이 없습니다.
Tasks
3DGSSemantic SegmentationSimilar Papers 제목 키워드 기반
FAST-Splat: Fast, Ambiguity-Free Semantics Transfer in Gaussian Splatting
We present FAST-Splat for fast, ambiguity-free semantic Gaussian Splatting, which seeks to address the main limitations of existing semantic Gaussian Splatting methods, namely: slow training and rendering speeds; high me…
Dimensionality ReductionGPUNatural Language QueriesObject Localization+3DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting
This paper addresses the limitations of existing 3D Gaussian Splatting (3DGS) methods, particularly their reliance on adaptive density control, which can lead to floating artifacts and inefficient resource usage. We prop…
Monocular Depth EstimationComputational EfficiencyFi-Gaussian: Frequency-Aware Implicit Gaussian Splatting for Single Image Dehazing
Single image dehazing continues to be hindered by the loss of high-frequency details and the difficulty of accurate physical scattering modeling. To address these issues, we propose Fi-Gaussian, a frequency-aware implici…
Single Image DehazingPoint CloudsPAGS: Priority-Adaptive Gaussian Splatting for Dynamic Driving Scenes
Reconstructing dynamic 3D urban scenes is crucial for autonomous driving, yet current methods face a stark trade-off between fidelity and computational cost. This inefficiency stems from their semantically agnostic desig…
Autonomous Driving3D ReconstructionGaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting
We introduce GaussianOcc, a systematic method that investigates the two usages of Gaussian splatting for fully self-supervised and efficient 3D occupancy estimation in surround views. First, traditional methods for self-…
Representation Learning