Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists

• URL: http://arxiv.org/abs/2603.09277v1
• Date: Tue, 10 Mar 2026 07:03:44 GMT
• Title: Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists
• Abstract summary: We propose novel training strategies and losses to shorten each Gaussian list used to render a pixel.<n>Specifically, we shrink the size of each Gaussian by resetting their scales regularly.<n>We also introduce an entropy constraint on the alpha blending procedure to sharpen the weight distribution of Gaussians along each ray.
• Score: 49.743765571852485
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian splatting (3DGS) has become a vital tool for learning a radiance field from multiple posed images. Although 3DGS shows great advantages over NeRF in terms of rendering quality and efficiency, it remains a research challenge to further improve the efficiency of learning 3D Gaussians. To overcome this challenge, we propose novel training strategies and losses to shorten each Gaussian list used to render a pixel, which speeds up the splatting by involving fewer Gaussians along a ray. Specifically, we shrink the size of each Gaussian by resetting their scales regularly, encouraging smaller Gaussians to cover fewer nearby pixels, which shortens the Gaussian lists of pixels. Additionally, we introduce an entropy constraint on the alpha blending procedure to sharpen the weight distribution of Gaussians along each ray, which drives dominant weights larger while making minor weights smaller. As a result, each Gaussian becomes more focused on the pixels where it is dominant, which reduces its impact on nearby pixels, leading to even shorter Gaussian lists. Eventually, we integrate our method into a rendering resolution scheduler which further improves efficiency through progressive resolution increase. We evaluate our method by comparing it with state-of-the-art methods on widely used benchmarks. Our results show significant advantages over others in efficiency without sacrificing rendering quality.

Related papers

• Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction [72.85652875805387]
  Free-Range Gaussians is a multi-view reconstruction method that predicts non-pixel, non-voxel-aligned 3D Gaussians from as few as four images.<n>Our generative formulation of reconstruction allows the model to be supervised with non-grid-aligned 3D data.
  arXiv  Detail & Related papers  (2026-04-06T17:24:18Z)
• SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM [46.618504092695254]
  Current methods usually use 3D Gaussians or view-tied 3D Gaussians to represent radiance fields in tracking and mapping.<n>We adopt pixel-aligned Gaussians but allow each Gaussian to adjust its position along its ray to maximize the rendering quality.<n>We report our evaluations on widely used benchmarks, justify our designs, and show advantages over the latest methods in view rendering, camera tracking, runtime, and storage complexity.
  arXiv  Detail & Related papers  (2026-03-22T04:42:02Z)
• Second-order Optimization of Gaussian Splats with Importance Sampling [51.95046424364725]
  3D Gaussian Splatting (3DGS) is widely used for novel view rendering due to its high quality and fast inference time.<n>We propose a novel second-order optimization strategy based on Levenberg-Marquardt (LM) and Conjugate Gradient (CG)<n>Our method achieves a $3times$ speedup over standard LM and outperforms Adam by $6times$ when the Gaussian count is low.
  arXiv  Detail & Related papers  (2025-04-17T12:52:08Z)
• ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes [81.48624894781257]
  3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis but is limited by the substantial number of Gaussian primitives required.<n>Recent methods address this issue by compressing the storage size of densified Gaussians, yet fail to preserve rendering quality and efficiency.<n>We propose ProtoGS to learn Gaussian prototypes to represent Gaussian primitives, significantly reducing the total Gaussian amount without sacrificing visual quality.
  arXiv  Detail & Related papers  (2025-03-21T18:55:14Z)
• Optimized Minimal 3D Gaussian Splatting [36.53860885419386]
  3D Gaussian Splatting (3DGS) has emerged as a powerful representation for real-time, high-performance rendering.<n> representing 3D scenes with numerous explicit Gaussian primitives imposes significant storage and memory overhead.<n>We propose a compact and precise attribute representation that efficiently captures both continuity and irregularity among primitives.
  arXiv  Detail & Related papers  (2025-03-21T07:41:45Z)
• Pushing Rendering Boundaries: Hard Gaussian Splatting [72.28941128988292]
  3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner.<n>We propose Hard Gaussian Splatting, dubbed HGS, which considers multi-view significant positional gradients and rendering errors to grow hard Gaussians.<n>Our method achieves state-of-the-art rendering quality while maintaining real-time efficiency.
  arXiv  Detail & Related papers  (2024-12-06T07:42:47Z)
• AdR-Gaussian: Accelerating Gaussian Splatting with Adaptive Radius [38.774337140911044]
  3D Gaussian Splatting (3DGS) is a recent explicit 3D representation that has achieved high-quality reconstruction and real-time rendering of complex scenes. We propose AdR-Gaussian, which moves part of serial culling in Render stage into the earlier Preprocess stage to enable parallel culling. Our contributions are threefold, achieving a rendering speed of 310% while maintaining equivalent or even better quality than the state-of-the-art.
  arXiv  Detail & Related papers  (2024-09-13T09:32:38Z)
• CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization [16.829825478946837]
  3D Gaussian Splatting (3DGS) is a new method for modeling and rendering 3D radiance fields. We show that our simple yet effective method can reduce the storage cost for 3DGS by 40 to 50x and rendering time by 2 to 3x with a very small drop in the quality of rendered images.
  arXiv  Detail & Related papers  (2023-11-30T00:29:13Z)
• LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS [55.85673901231235]
  We introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework.
  arXiv  Detail & Related papers  (2023-11-28T21:39:20Z)
• Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering [48.41629250718956]
  3D Gaussians have recently emerged as a highly efficient representation for 3D reconstruction and rendering. Despite its high rendering quality and speed at high resolutions, they both deteriorate drastically when rendered at lower resolutions or from far away camera position. We propose a multi-scale 3D Gaussian splatting algorithm, which maintains Gaussians at different scales to represent the same scene. Our algorithm can achieve 13%-66% PSNR and 160%-2400% rendering speed improvement at 4$times$-128$times$ scale rendering on Mip-NeRF360 dataset.
  arXiv  Detail & Related papers  (2023-11-28T03:31:35Z)

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.