Détail du document
Identifiant
oai:arXiv.org:2405.18784
Sujet
Computer Science - Computer Vision...Auteur
Zhang, Zhaoliang Song, Tianchen Lee, Yongjae Yang, Li Peng, Cheng Chellappa, Rama Fan, DeliangCatégorie
Computer Science
Année
2024
Date de référencement
05/06/2024
Mots clés
scene ratio pruning lp-3dgsRésumé
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
High-Frequency Repetitive Magnetic Stimulation at the Sacrum Alleviates Chronic Constipation in Parkinson’s Patients
magnetic stimulation parkinson’s significant patients scale sacrum pd hf-rms chronic constipation scores
