mlsanityData to 7 Oct 2026

Neo: Real-Time On-Device 3D Gaussian Splatting with Reuse-and-Update Sorting Acceleration

arXiv 2511.12930 ↗First posted 17 Nov 2025cs.AR cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 37 of its 100 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

37 of 100 references.

References · 37

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  6. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  7. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  9. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  11. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  12. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
25 more
  1. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  2. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 467
  3. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 420
  4. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 396
  5. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  6. 2024Mini-Splatting: Representing Scenes with a Constrained Number of Gaussianscited by 208
  7. 2023EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingScited by 191
  8. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  9. 2024Reducing the Memory Footprint of 3D Gaussian Splattingcited by 129
  10. 2023CompGS: Smaller and Faster Gaussian Splatting with Vector Quantizationcited by 127
  11. 2023Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstructioncited by 49
  12. 2022RT-NeRF: Real-Time On-Device Neural Radiance Fields Towards Immersive AR/VR Renderingcited by 35
  13. 2021DeepScaleTool : A Tool for the Accurate Estimation of Technology Scaling in the Deep-Submicron Eracited by 27
  14. 2024MetaSapiens: Real-Time Neural Rendering with Efficiency-Aware Pruning and Accelerated Foveated Renderingcited by 25
  15. 2018EVA2: Exploiting Temporal Redundancy in Live Computer Visioncited by 13
  16. 2023Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformerscited by 13
  17. 2018Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Visioncited by 10
  18. 2024Cicero: Addressing Algorithmic and Architectural Bottlenecks in Neural Rendering by Radiance Warping and Memory Optimizationscited by 10
  19. 2025GCC: A 3DGS Inference Architecture with Gaussian-Wise and Cross-Stage Conditional Processingcited by 10
  20. 2024DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analyticscited by 8
  21. 2025Gaussian Blending Unit: An Edge GPU Plug-in for Real-Time Gaussian-Based Rendering in AR/VRcited by 8
  22. 2023Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Designcited by 7
  23. 2025MixDiT: Accelerating Image Diffusion Transformer Inference with Mixed-Precision MX Quantizationcited by 7
  24. 2024Potamoi: Accelerating Neural Rendering via a Unified Streaming Architecturecited by 4
  25. 2019ASV: Accelerated Stereo Vision Systemcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026DeGS: A Scalable 3DGS Architecture via Decoupled Workload Parsing and Reorganizationcited by 1
  2. 2026TemporalGS: Training-Free Plug-and-Play Acceleration for 3D Gaussian Splatting Rendering via Temporal Priorscited by 0
  3. 2026Rendering 3D Gaussians on a Graph Processorcited by 0
  4. 2026From Splats to Silicon: Rethinking Computational Efficiency of 3DGScited by 0
  5. 2026Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generationcited by 0