Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruning

• URL: http://arxiv.org/abs/2406.18214v2
• Date: Mon, 29 Jul 2024 12:51:06 GMT
• Title: Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruning
• Authors: Muhammad Salman Ali, Maryam Qamar, Sung-Ho Bae, Enzo Tartaglione,
• Abstract summary: "Trimming the fat" is a post-hoc gradient-informed iterative pruning technique to eliminate redundant information encoded in the model. Our approach achieves around 50$times$ compression while preserving performance similar to the baseline model, and is able to speed-up computation up to 600 FPS.
• Score: 17.097742540845672
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent times, the utilization of 3D models has gained traction, owing to the capacity for end-to-end training initially offered by Neural Radiance Fields and more recently by 3D Gaussian Splatting (3DGS) models. The latter holds a significant advantage by inherently easing rapid convergence during training and offering extensive editability. However, despite rapid advancements, the literature still lives in its infancy regarding the scalability of these models. In this study, we take some initial steps in addressing this gap, showing an approach that enables both the memory and computational scalability of such models. Specifically, we propose "Trimming the fat", a post-hoc gradient-informed iterative pruning technique to eliminate redundant information encoded in the model. Our experimental findings on widely acknowledged benchmarks attest to the effectiveness of our approach, revealing that up to 75% of the Gaussians can be removed while maintaining or even improving upon baseline performance. Our approach achieves around 50$\times$ compression while preserving performance similar to the baseline model, and is able to speed-up computation up to 600 FPS.

Related papers

• ELMGS: Enhancing memory and computation scaLability through coMpression for 3D Gaussian Splatting [16.373800112150573]
  3D models have recently been popularized by the potentiality of end-to-end training offered by Neural Radiance Fields and 3D Gaussian Splatting models. We propose an approach enabling both memory and computation scalability of such models. Our results on popular benchmarks showcase the effectiveness of the proposed approach and open the road to the broad deployability of such a solution even on resource-constrained devices.
  arXiv  Detail & Related papers  (2024-10-30T17:01:28Z)
• Variational Bayes Gaussian Splatting [44.43761190929142]
  3D Gaussian Splatting has emerged as a promising approach for modeling 3D scenes using mixtures of Gaussians. We propose Variational Bayes Gaussian Splatting, a novel approach that frames training a Gaussian splat as variational inference over model parameters. Our experiments show that VBGS not only matches state-of-the-art performance on static datasets, but also enables continual learning from sequentially streamed 2D and 3D data.
  arXiv  Detail & Related papers  (2024-10-04T16:52:03Z)
• Mipmap-GS: Let Gaussians Deform with Scale-specific Mipmap for Anti-aliasing Rendering [81.88246351984908]
  We propose a unified optimization method to make Gaussians adaptive for arbitrary scales. Inspired by the mipmap technique, we design pseudo ground-truth for the target scale and propose a scale-consistency guidance loss to inject scale information into 3D Gaussians. Our method outperforms 3DGS in PSNR by an average of 9.25 dB for zoom-in and 10.40 dB for zoom-out.
  arXiv  Detail & Related papers  (2024-08-12T16:49:22Z)
• Taming 3DGS: High-Quality Radiance Fields with Limited Resources [50.92437599516609]
  3D Gaussian Splatting (3DGS) has transformed novel-view synthesis with its fast, interpretable, and high-fidelity rendering. We tackle the challenges of training and rendering 3DGS models on a budget. We derive faster, numerically equivalent solutions for gradient computation and attribute updates.
  arXiv  Detail & Related papers  (2024-06-21T20:44:23Z)
• RaDe-GS: Rasterizing Depth in Gaussian Splatting [32.38730602146176]
  Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering. Our work introduces a Chamfer distance error comparable to NeuraLangelo on the DTU dataset and maintains similar computational efficiency as the original 3D GS methods.
  arXiv  Detail & Related papers  (2024-06-03T15:56:58Z)
• GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [51.96353586773191]
  We introduce textbfGS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping system. Our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets.
  arXiv  Detail & Related papers  (2023-11-20T12:08:23Z)
• Post-Processing Temporal Action Detection [134.26292288193298]
  Temporal Action Detection (TAD) methods typically take a pre-processing step in converting an input varying-length video into a fixed-length snippet representation sequence. This pre-processing step would temporally downsample the video, reducing the inference resolution and hampering the detection performance in the original temporal resolution. We introduce a novel model-agnostic post-processing method without model redesign and retraining.
  arXiv  Detail & Related papers  (2022-11-27T19:50:37Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.