Abstract
Selecting informative camera views is critical for efficient training and adaptive refinement in 3D Gaussian Splatting, where each observation significantly influences model parameters. However, information-driven view-selection strategies can require repeated evaluations of expensive information-gain oracles as the number of candidate views increases. We propose LiTe-GS, an oracle-efficient method for next best view selection in 3D Gaussian Splatting. LiTe-GS reduces the number of information-oracle evaluations by performing randomized subset evaluation of candidate views rather than exhaustively scoring the full candidate pool. The resulting approach achieves expected $O(M\log(1/ε))$ oracle complexity with respect to the number of candidate views $M$, independent of the selection cardinality $K$, while providing an explicit trade-off between oracle efficiency and approximation quality through $ε$. We provide theoretical guarantees on oracle complexity and approximation performance under the proposed selection scheme. Experiments on Blender and Mip-NeRF 360 demonstrate that LiTe-GS maintains reconstruction quality comparable to Fisher-information-based baselines while substantially reducing the number of Fisher-oracle evaluations across different acquisition settings.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Pandey, V., Khass, A. M., & Motee, N. (2026). LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splatting. https://omanscience.com/en/articles/lite-gs-oracle-efficient-next-best-view-selection-for-3d-gaussian-splatting
MLA 9
Pandey, Vivek, et al. "LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splatting." https://omanscience.com/en/articles/lite-gs-oracle-efficient-next-best-view-selection-for-3d-gaussian-splatting.
Chicago (author–date)
Pandey, Vivek, Amirhossein Mollaei Khass, and Nader Motee. 2026. "LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splatting." https://omanscience.com/en/articles/lite-gs-oracle-efficient-next-best-view-selection-for-3d-gaussian-splatting.
Harvard
Pandey, V., Khass, A. M. and Motee, N. (2026) 'LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splatting', Available at: https://omanscience.com/en/articles/lite-gs-oracle-efficient-next-best-view-selection-for-3d-gaussian-splatting.
Vancouver
Pandey V, Khass AM, Motee N. LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splatting. https://omanscience.com/en/articles/lite-gs-oracle-efficient-next-best-view-selection-for-3d-gaussian-splatting
IEEE
V. Pandey, A. M. Khass, and N. Motee, "LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splatting," https://omanscience.com/en/articles/lite-gs-oracle-efficient-next-best-view-selection-for-3d-gaussian-splatting.