BROWSE
Detail
Journal Article
Fast Position Bit Depth Estimation for Near-Lossless Gaussian Splatting Representation
- Authors
- Jaiyoung Oh, Xin Li, Kwan-Jung Oh, Gwangsoon Lee, Euee S. Jang
- Issue Date
- 2025-10
- Citation
- Electronics Letters, v.61, no.1, pp.1-5
- ISSN
- 0013-5194
- Publisher
- John Wiley & Sons
- Language
- English
- Type
- Journal Article
- Abstract
- 3D Gaussian splatting enables real-time, photorealistic novel view synthesis using millions of 3D Gaussian primitives, but its adoption is hindered by high storage demands. This letter presents a fast statistical method to estimate the optimal position bit-depth for near-lossless compression, without rendering or PSNR computation. By modelling duplicated point ratios in training data and applying outlier detection to test data, our method predicts the minimal acceptable bit-depth. Experiments on multiple datasets show that the method takes approximately 1.24 s on average. This performance is achieved while preserving near-lossless quality, making the approach practical for real-time and resource-constrained applications.
- KSP Keywords
- Depth estimation, Multiple datasets, Novel view synthesis, Optimal position, Outlier Detection, Real-time, Resource-constrained, Statistical methods, Test data, bit depth, near-lossless compression
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
