From Splats to Silicon: Rethinking Computational Efficiency of 3DGS

• URL: http://arxiv.org/abs/2609.06157v1
• Date: Sat, 05 Sep 2026 15:57:26 GMT
• Title: From Splats to Silicon: Rethinking Computational Efficiency of 3DGS
• Abstract summary: 3D Gaussian splatting (3DGS) represents scenes with explicit primitives and supports real-time novel-view synthesis.<n>Its system efficiency varies substantially across scenes, viewpoints, rendering paths, and platform constraints.
• Score: 24.89564645819776
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian splatting (3DGS) represents scenes with explicit primitives and supports real-time novel-view synthesis, yet its system efficiency varies substantially across scenes, viewpoints, rendering paths, and platform constraints. Existing studies pursue efficiency through representation and algorithm design, GPU runtime optimization, and architectural support, but their reported gains correspond to different points along the rendering and update paths. Connecting these indicators to end-to-end system benefit requires tracing how each optimization changes Gaussian selection, screen-space work, data movement, and stage or frame time. We therefore use a workload-centric framework to connect representation and algorithm research, GPU runtimes, and hardware architectures and to identify recurring workload patterns. We complement literature analysis with reproduced measurements and controlled GPU profiling of selected implementations, relating workload counts to stage time and memory traffic. Together, these comparisons show that system gains depend on workload reductions reaching downstream execution, granularity matching each stage, and the cost of data transfers, synchronization, and cached results, gradients, and optimizer data. Building on these findings, we discuss more consistent evaluation under rendering-quality constraints and identify key directions for future system design.

Related papers

• Stipple: Real-Time Incremental Gaussian Splatting with Visual-Inertial Tracking [45.88028371034407]
  We propose a new method that tracks and reconstructs simultaneously in real-time by leveraging an efficient visual-inertial tracking system.<n>We show that many of the heavy preprocessing and training steps of 3DGS can be replaced with a more efficient incremental training strategy.
  arXiv  Detail & Related papers  (2026-08-02T02:17:05Z)
• Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects [26.144665202231014]
  Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token dominance.<n>We present a systematic taxonomy of efficiency techniques structured around the inference lifecycle, consisting of encoding, prefilling, and decoding.
  arXiv  Detail & Related papers  (2026-04-07T07:44:11Z)
• A Distributed Framework for Causal Modeling of Performance Variability in GPU Traces [0.43340169930181155]
  We present an end-to-end parallel performance analysis framework designed to handle multiple large-scale GPU traces efficiently.<n>Our proposed framework partitions and processes trace data concurrently and employs causal graph methods and parallel coordinating chart to expose performance variability and dependencies across execution flows.
  arXiv  Detail & Related papers  (2025-10-21T05:11:29Z)
• AllTracker: Efficient Dense Point Tracking at High Resolution [62.840979507761425]
  We introduce AllTracker, a model that estimates long-range point tracks by way of estimating the flow field between a query frame and every other frame of a video.<n>Unlike existing point tracking methods, our approach delivers high-resolution and dense (all-pixel) correspondence fields, which can be visualized as flow maps.<n>The model is fast and parameter-efficient (16 million parameters), and delivers state-of-the-art point tracking accuracy at high resolution (i.e., tracking 768x1024 pixels, on a 40G GPU)
  arXiv  Detail & Related papers  (2025-06-08T22:55:06Z)
• LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering [75.67501939005119]
  We present a novel level-of-detail (LOD) method for 3D Gaussian Splatting on memory-constrained devices.<n>Our approach iteratively selects optimal subsets of Gaussians based on camera distance.<n>Our method achieves state-of-the-art performance on both outdoor (Hierarchical 3DGS) and indoor (Zip-NeRF) datasets.
  arXiv  Detail & Related papers  (2025-05-29T06:50:57Z)
• Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better [61.381599921020175]
  Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts.<n>Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion.<n>We propose the Tracktention Layer, a novel architectural component that explicitly integrates motion information using point tracks.
  arXiv  Detail & Related papers  (2025-03-25T17:58:48Z)
• FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering [11.727367585102112]
  FlashGS is designed to facilitate the efficient differentiableization of 3D Gaussian Splatting. An extensive evaluation of FlashGS' performance has been conducted across a diverse spectrum of synthetic and real-world large-scale scenes. Results underscore the superior performance and resource optimization capabilities of FlashGS, positioning it as a formidable tool in the domain of 3D rendering.
  arXiv  Detail & Related papers  (2024-08-15T06:27:42Z)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)
• SGTR+: End-to-end Scene Graph Generation with Transformer [42.396971149458324]
  Scene Graph Generation (SGG) remains a challenging visual understanding task due to its compositional property. Most previous works adopt a bottom-up, two-stage or point-based, one-stage approach, which often suffers from high time complexity or suboptimal designs. We propose a novel SGG method to address the aforementioned issues, formulating the task as a bipartite graph construction problem.
  arXiv  Detail & Related papers  (2024-01-23T15:18:20Z)
• Performance Embeddings: A Similarity-based Approach to Automatic Performance Optimization [71.69092462147292]
  Performance embeddings enable knowledge transfer of performance tuning between applications. We demonstrate this transfer tuning approach on case studies in deep neural networks, dense and sparse linear algebra compositions, and numerical weather prediction stencils.
  arXiv  Detail & Related papers  (2023-03-14T15:51:35Z)
• SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion [86.77318031029404]
  We propose a framework that performs scene reconstruction and semantic scene completion jointly in an incremental and real-time manner. Our framework relies on a novel neural architecture designed to process occupancy maps and leverages voxel states to accurately and efficiently fuse semantic completion with the 3D global model.
  arXiv  Detail & Related papers  (2020-10-26T15:31:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.