methods_compression.bib

@misc{wang2024contextgs,
  title={ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Model},
  author={Wang, Yufei and Li, Zhihao and Guo, Lanqing and Yang, Wenhan and Kot, Alex C and Wen, Bihan},
  booktitle={Neural Information Processing Systems},
  year={2024},
  shortname={ContextGS},
  url={https://github.com/wyf0912/ContextGS},
  abstract={
      Recently, 3D Gaussian Splatting (3DGS) has become a promising framework for novel view synthesis, offering fast rendering speeds and high fidelity. However, the large number of Gaussians and their associated attributes require effective compression techniques. Existing methods primarily compress neural Gaussians individually and independently, i.e., coding all the neural Gaussians at the same time, with little design for their interactions and spatial dependence. Inspired by the effectiveness of the context model in image compression, we propose the first autoregressive model at the anchor level for 3DGS compression in this work. We divide anchors into different levels and the anchors that are not coded yet can be predicted based on the already coded ones in all the coarser levels, leading to more accurate modeling and higher coding efficiency. To further improve the efficiency of entropy coding, e.g., to code the coarsest level with no already coded anchors, we propose to introduce a low-dimensional quantized feature as the hyperprior for each anchor, which can be effectively compressed. Our work pioneers the context model in the anchor level for 3DGS representation, yielding an impressive size reduction of over 100 times compared to vanilla 3DGS and 15 times compared to the most recent state-of-the-art work Scaffold-GS, while achieving comparable or even higher rendering quality.
  }
}

@misc{morgenstern2024compact,
      title={Compact 3D Scene Representation via Self-Organizing Gaussian Grids}, 
      author={Wieland Morgenstern and Florian Barthel and Anna Hilsmann and Peter Eisert},
      year={2024},
      booktitle={European Conference on Computer Vision},
      eprint={2312.13299},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://fraunhoferhhi.github.io/Self-Organizing-Gaussians/},
      abstract={3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of static 3D scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterization allowing for very fast rendering at high-quality. However, the storage size is significantly higher, which hinders practical deployment, e.g.~on resource constrained devices. In this paper, we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage requirements without compromising visual quality during rendering. Central to our idea is the explicit exploitation of perceptual redundancies present in natural scenes. In essence, the inherent nature of a scene allows for numerous permutations of Gaussian parameters to equivalently represent it. To this end, we propose a novel highly parallel algorithm that regularly arranges the high-dimensional Gaussian parameters into a 2D grid while preserving their neighborhood structure. During training, we further enforce local smoothness between the sorted parameters in the grid. The uncompressed Gaussians use the same structure as 3DGS, ensuring a seamless integration with established renderers. Our method achieves a reduction factor of 17x to 42x in size for complex scenes with no increase in training time, marking a substantial leap forward in the domain of 3D scene distribution and consumption.},
      shortname={SOG},
}


@misc{lee2024compact,
      title={Compact 3D Gaussian Representation for Radiance Field}, 
      author={Joo Chan Lee and Daniel Rho and Xiangyu Sun and Jong Hwan Ko and Eunbyung Park},
      year={2024},
      booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      pages={21719--21728},
      url={https://maincold2.github.io/c3dgs/},
      abstract={Neural Radiance Fields (NeRFs) have demonstrated remarkable potential in capturing complex 3D scenes with high fidelity. However, one persistent challenge that hinders the widespread adoption of NeRFs is the computational bottleneck due to the volumetric rendering. On the other hand, 3D Gaussian splatting (3DGS) has recently emerged as an alternative representation that leverages a 3D Gaussisan-based representation and adopts the rasterization pipeline to render the images rather than volumetric rendering, achieving very fast rendering speed and promising image quality. However, a significant drawback arises as 3DGS entails a substantial number of 3D Gaussians to maintain the high fidelity of the rendered images, which requires a large amount of memory and storage. To address this critical issue, we place a specific emphasis on two key objectives: reducing the number of Gaussian points without sacrificing performance and compressing the Gaussian attributes, such as view-dependent color and covariance. To this end, we propose a learnable mask strategy that significantly reduces the number of Gaussians while preserving high performance. In addition, we propose a compact but effective representation of view-dependent color by employing a grid-based neural field rather than relying on spherical harmonics. Finally, we learn codebooks to compactly represent the geometric attributes of Gaussian by vector quantization. With model compression techniques such as quantization and entropy coding, we consistently show over 25× reduced storage and enhanced rendering speed, while maintaining the quality of the scene representation, compared to 3DGS. Our work provides a comprehensive framework for 3D scene representation, achieving high performance, fast training, compactness, and real-time rendering. Our project page is available at https://maincold2.github.io/c3dgs/.},
      shortname={Compact3DGS},
}

@misc{navaneet2023compact3d,
      title={Compact3D: Compressing Gaussian Splat Radiance Field Models with Vector Quantization}, 
      author={KL Navaneet and Kossar Pourahmadi Meibodi and Soroush Abbasi Koohpayegani and Hamed Pirsiavash},
      year={2024},
      booktitle={European Conference on Computer Vision},
      eprint={2311.18159},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://ucdvision.github.io/compact3d/},
      abstract={3D Gaussian Splatting is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods. However, it comes with a drawback in the much larger storage demand compared to NeRF methods since it needs to store the parameters for several 3D Gaussians. We notice that many Gaussians may share similar parameters, so we introduce a simple vector quantization method based on \kmeans algorithm to quantize the Gaussian parameters. Then, we store the small codebook along with the index of the code for each Gaussian. Moreover, we compress the indices further by sorting them and using a method similar to run-length encoding. We do extensive experiments on standard benchmarks as well as a new benchmark which is an order of magnitude larger than the standard benchmarks. We show that our simple yet effective method can reduce the storage cost for the original 3D Gaussian Splatting method by a factor of almost 20× with a very small drop in the quality of rendered images.},
      shortname={Compact3D},
}

@misc{fan2024lightgaussian,
      title={LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS}, 
      author={Zhiwen Fan and Kevin Wang and Kairun Wen and Zehao Zhu and Dejia Xu and Zhangyang Wang},
      year={2024},
      eprint={2311.17245},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://lightgaussian.github.io/},
      abstract={Recent advancements in real-time neural rendering using point-based techniques have paved the way for the widespread adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting come with a substantial storage overhead caused by growing the SfM points to millions, often demanding gigabyte-level disk space for a single unbounded scene, posing significant scalability challenges and hindering the splatting efficiency. To address this challenge, we introduce LightGaussian, a novel method designed to transform 3D Gaussians into a more efficient and compact format. Drawing inspiration from the concept of Network Pruning, LightGaussian identifies Gaussians that are insignificant in contributing to the scene reconstruction and adopts a pruning and recovery process, effectively reducing redundancy in Gaussian counts while preserving visual effects. Additionally, LightGaussian employs distillation and pseudo-view augmentation to distill spherical harmonics to a lower degree, allowing knowledge transfer to more compact representations while maintaining reflectance. Furthermore, we propose a hybrid scheme, VecTree Quantization, to quantize all attributes, resulting in lower bitwidth representations with minimal accuracy losses. In summary, LightGaussian achieves an averaged compression rate over 15x while boosting the FPS from 139 to 215, enabling an efficient representation of complex scenes on Mip-NeRF 360, Tank and Temple datasets.},
      shortname={LightGaussian},
}

@misc{chen2024hac,
      title={HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression}, 
      author={Yihang Chen and Qianyi Wu and Jianfei Cai and Mehrtash Harandi and Weiyao Lin},
      year={2024},
      booktitle={European Conference on Computer Vision},
      eprint={2403.14530},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://yihangchen-ee.github.io/project_hac/},
      abstract={3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To address this, we make use of the relations between the unorganized anchors and the structured hash grid, leveraging their mutual information for context modeling, and propose a Hash-grid Assisted Context (HAC) framework for highly compact 3DGS representation. Our approach introduces a binary hash grid to establish continuous spatial consistencies, allowing us to unveil the inherent spatial relations of anchors through a carefully designed context model. To facilitate entropy coding, we utilize Gaussian distributions to accurately estimate the probability of each quantized attribute, where an adaptive quantization module is proposed to enable high-precision quantization of these attributes for improved fidelity restoration. Additionally, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Importantly, our work is the pioneer to explore context-based compression for 3DGS representation, resulting in a remarkable size reduction of over 75× compared to vanilla 3DGS, while simultaneously improving fidelity, and achieving over 11× size reduction over SOTA 3DGS compression approach Scaffold-GS. Our code is available here: https://github.com/YihangChen-ee/HAC},
      shortname={HAC},
}

@misc{niedermayr2024compressed,
      title={Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis}, 
      author={Simon Niedermayr and Josef Stumpfegger and Rüdiger Westermann},
      year={2024},
      booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      pages={10349--10358},
      url={https://keksboter.github.io/c3dgs/},
      abstract={Recently, high-fidelity scene reconstruction with an optimized 3D Gaussian splat representation has been introduced for novel view synthesis from sparse image sets. Making such representations suitable for applications like network streaming and rendering on low-power devices requires significantly reduced memory consumption as well as improved rendering efficiency. We propose a compressed 3D Gaussian splat representation that utilizes sensitivity-aware vector clustering with quantization-aware training to compress directional colors and Gaussian parameters. The learned codebooks have low bitrates and achieve a compression rate of up to 31× on real-world scenes with only minimal degradation of visual quality. We demonstrate that the compressed splat representation can be efficiently rendered with hardware rasterization on lightweight GPUs at up to 4× higher framerates than reported via an optimized GPU compute pipeline. Extensive experiments across multiple datasets demonstrate the robustness and rendering speed of the proposed approach.},
      shortname={Compressed3D},
}

@article{papantonakis2024reducing,
  title={Reducing the Memory Footprint of 3D Gaussian Splatting},
  author={Papantonakis, Panagiotis and Kopanas, Georgios and Kerbl, Bernhard and Lanvin, Alexandre and Drettakis, George},
  journal={Proceedings of the ACM on Computer Graphics and Interactive Techniques},
  volume={7},
  number={1},
  pages={1--17},
  year={2024},
  month={May},
  publisher={ACM New York, NY, USA},
  url={https://repo-sam.inria.fr/fungraph/reduced_3dgs/},
  abstract={3D Gaussian splatting provides excellent visual quality for novel view synthesis, with fast training and real-time rendering; unfortunately, the memory requirements of this method for storing and transmission are unreasonably high. We first analyze the reasons for this, identifying three main areas where storage can be reduced: the number of 3D Gaussian primitives used to represent a scene, the number of coefficients for the spherical harmonics used to represent directional radiance, and the precision required to store Gaussian primitive attributes. We present a solution to each of these issues. First, we propose an efficient, resolution-aware primitive pruning approach, reducing the primitive count by half. Second, we introduce an adaptive adjustment method to choose the number of coefficients used to represent directional radiance for each Gaussian primitive, and finally a codebook-based quantization method, together with a half-float representation for further memory reduction. Taken together, these three components result in a ×27 reduction in overall size on disk on the standard datasets we tested, along with a ×1.7 speedup in rendering speed. We demonstrate our method on standard datasets and show how our solution results in significantly reduced download times when using the method on a mobile device.},
  shortname={Reduced3DGS},
}

@misc{girish2024eagles,
      title={EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS}, 
      author={Sharath Girish and Kamal Gupta and Abhinav Shrivastava},
      year={2024},
      eprint={2312.04564},
      archivePrefix={arXiv},
      primaryClass={id='cs.CV' full_name='Computer Vision and Pattern Recognition' is_active=True alt_name=None in_archive='cs' is_general=False description='Covers image processing, computer vision, pattern recognition, and scene understanding. Roughly includes material in ACM Subject Classes I.2.10, I.4, and I.5.'},
      url={https://efficientgaussian.github.io/},
      abstract={Recently, 3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Neural Radiance Fields (NeRFs). Through rapid, differentiable rasterization of 3D Gaussians, 3D-GS achieves real-time rendering and accelerated training. They, however, demand substantial memory resources for both training and storage, as they require millions of Gaussians in their point cloud representation for each scene. We present a technique utilizing quantized embeddings to significantly reduce per-point memory storage requirements and a coarse-to-fine training strategy for a faster and more stable optimization of the Gaussian point clouds. Our approach develops a pruning stage which results in scene representations with fewer Gaussians, leading to faster training times and rendering speeds for real-time rendering of high resolution scenes. We reduce storage memory by more than an order of magnitude all while preserving the reconstruction quality. We validate the effectiveness of our approach on a variety of datasets and scenes preserving the visual quality while consuming 10-20x lesser memory and faster training/inference speed. Project page and code is available this https URL},
      shortname={EAGLES},
}

@misc{sun2024f3dgs,
      title={F-3DGS: Factorized Coordinates and Representations for 3D Gaussian Splatting}, 
      author={Xiangyu Sun and Joo Chan Lee and Daniel Rho and Jong Hwan Ko and Usman Ali and Eunbyung Park},
      year={2024},
      eprint={2405.17083},
      archivePrefix={arXiv},
      primaryClass={id='cs.CV' full_name='Computer Vision and Pattern Recognition' is_active=True alt_name=None in_archive='cs' is_general=False description='Covers image processing, computer vision, pattern recognition, and scene understanding. Roughly includes material in ACM Subject Classes I.2.10, I.4, and I.5.'},
      abstract={The neural radiance field (NeRF) has made significant strides in representing 3D scenes and synthesizing novel views. Despite its advancements, the high computational costs of NeRF have posed challenges for its deployment in resource-constrained environments and real-time applications. As an alternative to NeRF-like neural rendering methods, 3D Gaussian Splatting (3DGS) offers rapid rendering speeds while maintaining excellent image quality. However, as it represents objects and scenes using a myriad of Gaussians, it requires substantial storage to achieve high-quality representation. To mitigate the storage overhead, we propose Factorized 3D Gaussian Splatting (F-3DGS), a novel approach that drastically reduces storage requirements while preserving image quality. Inspired by classical matrix and tensor factorization techniques, our method represents and approximates dense clusters of Gaussians with significantly fewer Gaussians through efficient factorization. We aim to efficiently represent dense 3D Gaussians by approximating them with a limited amount of information for each axis and their combinations. This method allows us to encode a substantially large number of Gaussians along with their essential attributes -- such as color, scale, and rotation -- necessary for rendering using a relatively small number of elements. Extensive experimental results demonstrate that F-3DGS achieves a significant reduction in storage costs while maintaining comparable quality in rendered images.},
      url={https://xiangyu1sun.github.io/Factorize-3DGS/}, 
      shortname={F-3DGS},
}

@misc{lu2024scaffold,
      title={Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering}, 
      author={Tao Lu and Mulin Yu and Linning Xu and Yuanbo Xiangli and Limin Wang and Dahua Lin and Bo Dai},
      year={2024},
      booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      pages={20654--20664},
      abstract={Neural rendering methods have significantly advanced photo-realistic 3D scene rendering in various academic and industrial applications. The recent 3D Gaussian Splatting method has achieved the state-of-the-art rendering quality and speed combining the benefits of both primitive-based representations and volumetric representations. However, it often leads to heavily redundant Gaussians that try to fit every training view, neglecting the underlying scene geometry. Consequently, the resulting model becomes less robust to significant view changes, texture-less area and lighting effects. We introduce Scaffold-GS, which uses anchor points to distribute local 3D Gaussians, and predicts their attributes on-the-fly based on viewing direction and distance within the view frustum. Anchor growing and pruning strategies are developed based on the importance of neural Gaussians to reliably improve the scene coverage. We show that our method effectively reduces redundant Gaussians while delivering high-quality rendering. We also demonstrates an enhanced capability to accommodate scenes with varying levels-of-detail and view-dependent observations, without sacrificing the rendering speed.},
      url={https://city-super.github.io/scaffold-gs/}, 
      shortname={Scaffold-GS},
}

@misc{wang2024end,
      title={End-to-End Rate-Distortion Optimized 3D Gaussian Representation}, 
      author={Henan Wang and Hanxin Zhu and Tianyu He and Runsen Feng and Jiajun Deng and Jiang Bian and Zhibo Chen},
      year={2024},
      booktitle={European Conference on Computer Vision},
      eprint={2406.01597},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      abstract={3D Gaussian Splatting (3DGS) has become an emerging technique with remarkable potential in 3D representation and image rendering. However, the substantial storage overhead of 3DGS significantly impedes its practical applications. In this work, we formulate the compact 3D Gaussian learning as an end-to-end Rate-Distortion Optimization (RDO) problem and propose RDO-Gaussian that can achieve flexible and continuous rate control. RDO-Gaussian addresses two main issues that exist in current schemes: 1) Different from prior endeavors that minimize the rate under the fixed distortion, we introduce dynamic pruning and entropy-constrained vector quantization (ECVQ) that optimize the rate and distortion at the same time. 2) Previous works treat the colors of each Gaussian equally, while we model the colors of different regions and materials with learnable numbers of parameters. We verify our method on both real and synthetic scenes, showcasing that RDO-Gaussian greatly reduces the size of 3D Gaussian over 40×, and surpasses existing methods in rate-distortion performance.},
      url={https://rdogaussian.github.io/}, 
      shortname={RDO-Gaussian},
}

@inproceedings{xie2024mesongs,
    title={MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation},
    author={Xie, Shuzhao and Zhang, Weixiang and Tang, Chen and Bai, Yunpeng and Lu, Rongwei and Ge, Shijia and Wang, Zhi},
    booktitle={European Conference on Computer Vision},
    year={2024},
    organization={Springer},
    abstract={3D Gaussian Splatting demonstrates excellent quality and speed in novel view synthesis. Nevertheless, the significant size of the 3D Gaussians presents challenges for transmission and storage. Current approaches employ compact models to compress the substantial volume and attributes of 3D Gaussians, along with intensive training to uphold quality. These endeavors demand considerable finetuning time, presenting formidable hurdles for practical deployment. To this end, we propose MesonGS, a codec for post-training compression of 3D Gaussians. Initially, we introduce a measurement criterion that considers both view-dependent and view-independent factors to assess the impact of each Gaussian point on the rendering output, enabling the removal of insignificant points. Subsequently, we decrease the entropy of attributes through two transformations that complement subsequent entropy coding techniques to enhance the file compression rate. More specifically, we first replace the rotation quaternion with Euler angles; then, we apply region adaptive hierarchical transform (RAHT) to key attributes to reduce entropy. Lastly, we suggest block quantization to control quantization granularity, thereby avoiding excessive information loss caused by quantization. Moreover, a finetune scheme is introduced to restore quality. Extensive experiments demonstrate that MesonGS significantly reduces the size of 3D Gaussians while preserving competitive quality.},
    url={https://shuzhaoxie.github.io/mesongs/},
    shortname={MesonGS},
}

@misc{hu2024gsplat,
    title={gsplat compression}, 
    author={Jeffrey Hu and Ruilong Li and Vickie Ye and Angjoo Kanazawa},
    year={2024},
    archivePrefix={arXiv},
    url={https://github.com/w-m/3dgs-compression-survey/pull/7},
    shortname={gsplat},
}

@article{wu2024implicit,
  title={Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representation},
  author={Wu, Minye and Tuytelaars, Tinne},
  journal={arXiv preprint arXiv:2408.10041},
  year={2024},
  url={https://www.arxiv.org/abs/2408.10041},
  abstract={Recent advancements in photo-realistic novel view synthesis have been significantly driven by Gaussian Splatting (3DGS). Nevertheless, the explicit nature of 3DGS data entails considerable storage requirements, highlighting a pressing need for more efficient data representations. To address this, we present Implicit Gaussian Splatting (IGS), an innovative hybrid model that integrates explicit point clouds with implicit feature embeddings through a multi-level tri-plane architecture. This architecture features 2D feature grids at various resolutions across different levels, facilitating continuous spatial domain representation and enhancing spatial correlations among Gaussian primitives. Building upon this foundation, we introduce a level-based progressive training scheme, which incorporates explicit spatial regularization. This method capitalizes on spatial correlations to enhance both the rendering quality and the compactness of the IGS representation. Furthermore, we propose a novel compression pipeline tailored for both point clouds and 2D feature grids, considering the entropy variations across different levels. Extensive experimental evaluations demonstrate that our algorithm can deliver high-quality rendering using only a few MBs, effectively balancing storage efficiency and rendering fidelity, and yielding results that are competitive with the state-of-the-art.},
  shortname={IGS}
}

@inproceedings{liu2024compgs,
  title={CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting},
  author={Liu, Xiangrui and Wu, Xinju and Zhang, Pingping and Wang, Shiqi and Li, Zhu and Kwong, Sam},
  booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},
  year={2024},
  url={https://www.arxiv.org/abs/2404.09458},
  abstract={Gaussian splatting, renowned for its exceptional rendering quality and efficiency, has emerged as a prominent technique in 3D scene representation. However, the substantial data volume of Gaussian splatting impedes its practical utility in real-world applications. Herein, we propose an efficient 3D scene representation, named Compressed Gaussian Splatting (CompGS), which harnesses compact Gaussian primitives for faithful 3D scene modeling with a remarkably reduced data size. To ensure the compactness of Gaussian primitives, we devise a hybrid primitive structure that captures predictive relationships between each other. Then, we exploit a small set of anchor primitives for prediction, allowing the majority of primitives to be encapsulated into highly compact residual forms. Moreover, we develop a rate-constrained optimization scheme to eliminate redundancies within such hybrid primitives, steering our CompGS towards an optimal trade-off between bitrate consumption and representation efficacy. Experimental results show that the proposed CompGS significantly outperforms existing methods, achieving superior compactness in 3D scene representation without compromising model accuracy and rendering quality. Our code will be released on GitHub for further research.},
  shortname={CompGS}
}