mlsanityData to 7 Oct 2026

SAGE: Semantic-Driven Adaptive Gaussian Splatting in Extended Reality

arXiv 2503.16747 ↗First posted 20 Mar 2025cs.GR cs.CV cs.MMcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 27 references that are in the map. First posted on arXiv 20 Mar 2025.

Builds on

15 of 27 references.

References · 15

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  6. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 420
  7. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  8. 2024Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussianscited by 225
  9. 2023Multi-Scale 3D Gaussian Splatting for Anti-Aliased Renderingcited by 137
  10. 2024FLoD: Integrating Flexible Level of Detail into 3D Gaussian Splatting for Customizable Renderingcited by 26
  11. 2021Appearance-Driven Automatic 3D Model Simplificationcited by 24
  12. 2019Point Cloud Rendering after Coding: Impacts on Subjective and Objective Qualitycited by 22
3 more
  1. 2021DeepLab2: A TensorFlow Library for Deep Labelingcited by 22
  2. 2024Semantics-Controlled Gaussian Splatting for Outdoor Scene Reconstruction and Rendering in Virtual Realitycited by 10
  3. 2020Convolutional Neural Networks for Continuous QoE Prediction in Video Streaming Servicescited by 4

Built on by

Not cited yet.