Dokumentdetails
ID
oai:arXiv.org:2405.18784
Thema
Computer Science - Computer Vision...Autor
Zhang, Zhaoliang Song, Tianchen Lee, Yongjae Yang, Li Peng, Cheng Chellappa, Rama Fan, DeliangKategorie
Computer Science
Jahr
2024
Auflistungsdatum
05.06.2024
Schlüsselwörter
scene ratio pruning lp-3dgsZusammenfassung
Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed.
However, as a point-based scene representation, 3DGS potentially generates a large number of Gaussians to fit the scene, leading to high memory usage.
Improvements that have been proposed require either an empirical and preset pruning ratio or importance score threshold to prune the point cloud.
Such hyperparamter requires multiple rounds of training to optimize and achieve the maximum pruning ratio, while maintaining the rendering quality for each scene.
In this work, we propose learning-to-prune 3DGS (LP-3DGS), where a trainable binary mask is applied to the importance score that can find optimal pruning ratio automatically.
Instead of using the traditional straight-through estimator (STE) method to approximate the binary mask gradient, we redesign the masking function to leverage the Gumbel-Sigmoid method, making it differentiable and compatible with the existing training process of 3DGS.
Extensive experiments have shown that LP-3DGS consistently produces a good balance that is both efficient and high quality.
Zhang, Zhaoliang,Song, Tianchen,Lee, Yongjae,Yang, Li,Peng, Cheng,Chellappa, Rama,Fan, Deliang, 2024, LP-3DGS: Learning to Prune 3D Gaussian Splatting
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
methods salience efficiency quantization language slim-llm llms
Prediction Models for Suicide Attempts among Adolescents Using Machine Learning Techniques
using data ml prediction 0 suicide adolescents
