Research map / 3D vision / Gaussian splatting
Spherical Bayesian Experimental Design for Active View Selection in 3D Gaussian Splatting
Yan Song, Yunfei Guo, Guyeli Yang, Li He, Chenglong Li, Huanzhen Wang, Bailin HE, Qiao Sun, Zhong Jiangwei, Shizeng Zhang, Nuo Chen, Yan Wang and 1 more
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a spherical Bayesian experimental design approach for active view selection in 3D Gaussian Splatting that aims to combine information-theoretic grounding with computational efficiency.
Problem
Active view selection for 3D Gaussian Splatting needs information-theoretic grounding, computational efficiency, and strong reconstruction quality; existing information-theoretic methods rely on costly Fisher computation under a Laplace approximation over the full parameter space, while faster alter
Approach
Reframes view selection as Bayesian experimental design on a spherical parameterization to avoid full-parameter-space Fisher computation while retaining an information-theoretic objective (method details not stated in the abstract).
Experimental setup
Builds on: Laplace approximation Fisher information
Closest papers by meaning
- Metropolis-Hastings Sampling for 3D Gaussian Reconstruction (NeurIPS 2025 · similarity 0.91)
- POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality (CVPR 2025 · similarity 0.89)
- Variational Multi-scale Representation for Estimating Uncertainty in 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.89)
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting (NeurIPS 2026 · similarity 0.89)
- 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization (NeurIPS 2024 · similarity 0.89)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
