Neo: Real-Time On-Device 3D Gaussian Splatting with Reuse-and-Update Sorting Acceleration
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909906310791168 |
|---|---|
| author | Oh, Changhun Oh, Seongryong Hwang, Jinwoo Kim, Yoonsung Sharma, Hardik Park, Jongse |
| author_facet | Oh, Changhun Oh, Seongryong Hwang, Jinwoo Kim, Yoonsung Sharma, Hardik Park, Jongse |
| contents | 3D Gaussian Splatting (3DGS) rendering in real-time on resource-constrained devices is essential for delivering immersive augmented and virtual reality (AR/VR) experiences. However, existing solutions struggle to achieve high frame rates, especially for high-resolution rendering. Our analysis identifies the sorting stage in the 3DGS rendering pipeline as the major bottleneck due to its high memory bandwidth demand. This paper presents Neo, which introduces a reuse-and-update sorting algorithm that exploits temporal redundancy in Gaussian ordering across consecutive frames, and devises a hardware accelerator optimized for this algorithm. By efficiently tracking and updating Gaussian depth ordering instead of re-sorting from scratch, Neo significantly reduces redundant computations and memory bandwidth pressure. Experimental results show that Neo achieves up to 10.0x and 5.6x higher throughput than state-of-the-art edge GPU and ASIC solution, respectively, while reducing DRAM traffic by 94.5% and 81.3%. These improvements make high-quality and low-latency on-device 3D rendering more practical. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12930 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neo: Real-Time On-Device 3D Gaussian Splatting with Reuse-and-Update Sorting Acceleration Oh, Changhun Oh, Seongryong Hwang, Jinwoo Kim, Yoonsung Sharma, Hardik Park, Jongse Hardware Architecture Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) rendering in real-time on resource-constrained devices is essential for delivering immersive augmented and virtual reality (AR/VR) experiences. However, existing solutions struggle to achieve high frame rates, especially for high-resolution rendering. Our analysis identifies the sorting stage in the 3DGS rendering pipeline as the major bottleneck due to its high memory bandwidth demand. This paper presents Neo, which introduces a reuse-and-update sorting algorithm that exploits temporal redundancy in Gaussian ordering across consecutive frames, and devises a hardware accelerator optimized for this algorithm. By efficiently tracking and updating Gaussian depth ordering instead of re-sorting from scratch, Neo significantly reduces redundant computations and memory bandwidth pressure. Experimental results show that Neo achieves up to 10.0x and 5.6x higher throughput than state-of-the-art edge GPU and ASIC solution, respectively, while reducing DRAM traffic by 94.5% and 81.3%. These improvements make high-quality and low-latency on-device 3D rendering more practical. |
| title | Neo: Real-Time On-Device 3D Gaussian Splatting with Reuse-and-Update Sorting Acceleration |
| topic | Hardware Architecture Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.12930 |