Masked Space-time Hash Encoding For Efficient Dynamic Scene Reconstruction
2023 · Feng Wang, Zilong Chen, Guokang Wang, et al.
Abstract
In this paper, we propose the Masked Space-Time Hash encoding (MSTH), a novel method for efficiently reconstructing dynamic 3D scenes from multi-view or monocular videos. Based on the observation that dynamic scenes often contain substantial static areas that result in redundancy in storage and computations, MSTH represents a dynamic scene as a weighted combination of a 3D hash encoding and a 4D hash encoding. The weights for the two components are represented by a learnable mask which is guided by an uncertainty-based objective to reflect the spatial and temporal importance of each 3D position. With this design, our method can reduce the hash collision rate by avoiding redundant queries and modifications on static areas, making it feasible to represent a large number of space-time voxels by hash tables with small size.Besides, without the requirements to fit the large numbers of temporally redundant features independently, our method is easier to optimize and converge rapidly with onl
Authors
(none)
Tags
Stats
Related papers
- Hashmod: A Hashing Method For Scalable 3D Object Detection (2016)10.07
- Encode The Unseen: Predictive Video Hashing For Scalable Mid-stream Retrieval (2020)3.58
- Dual-stream Knowledge-preserving Hashing For Unsupervised Video Retrieval (2023)9.23
- Self-supervised Video Hashing With Hierarchical Binary Auto-encoder (2018)17.81
- CHAIN: Exploring Global-local Spatio-temporal Information For Improved Self-supervised Video Hashing (2023)8.60
- Multi-focused Video Group Activities Hashing (2025)0.00
- Deep Heterogeneous Hashing For Face Video Retrieval (2019)9.92
- Contrastive Masked Auto-encoders Based Self-supervised Hashing For 2D Image And 3D Point Cloud Cross-modal Retrieval (2024)2.26