One is all: Bridging the gap between neural radiance fields architectures with progressive volume distillation

S Fang, W Xu, H Wang, Y Yang, Y Wang… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Abstract Neural Radiance Fields (NeRF) methods have proved effective as compact, high-
quality and versatile representations for 3D scenes, and enable downstream tasks such as …

Pvd-al: Progressive volume distillation with active learning for efficient conversion between different nerf architectures

S Fang, Y Wang, Y Yang, W Xu, H Wang… - arxiv preprint arxiv …, 2023 - arxiv.org
Neural Radiance Fields (NeRF) have been widely adopted as practical and versatile
representations for 3D scenes, facilitating various downstream tasks. However, different …

Case study of video compression via tensor train and Tucker decompositions

AA Kurilovich, SA Matveev - Computational Mathematics and Modeling, 2023 - Springer
This work represents a study of the capabilities of an approach for lossy video compression
based on the tensor train and Tucker tensor formats. The TTSVD and st-HOSVD algorithms …