Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruning
- URL: http://arxiv.org/abs/2406.18214v1
- Date: Wed, 26 Jun 2024 09:57:55 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 600FPS.
- 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
- 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) - latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction [48.86083272054711]
latentSplat is a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture.
We show that latentSplat outperforms previous works in reconstruction quality and generalization, while being fast and scalable to high-resolution data.
arXiv Detail & Related papers (2024-03-24T20:48:36Z) - 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) - Rethinking Deconvolution for 2D Human Pose Estimation Light yet Accurate
Model for Real-time Edge Computing [0.0]
This system was found to be very accurate and achieved a 94.5% accuracy of SOTA HRNet 256x192.
Our model adopts an encoder-decoder architecture and is carefully downsized to improve its efficiency.
arXiv Detail & Related papers (2021-11-08T01:44:46Z) - 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.