Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Next Best View Selections for Semantic and Dynamic 3D Gaussian Splatting

About

Understanding semantics and dynamics has been crucial for embodied agents in various tasks. Both tasks have much more data redundancy than the static scene understanding task. We formulate the view selection problem as an active learning problem, where the goal is to prioritize frames that provide the greatest information gain for model training. To this end, we propose an active learning algorithm with Fisher Information that quantifies the informativeness of candidate views with respect to both semantic Gaussian parameters and deformation networks. This formulation allows our method to jointly handle semantic reasoning and dynamic scene modeling, providing a principled alternative to heuristic or random strategies. We evaluate our method on large-scale static images and dynamic video datasets by selecting informative frames from multi-camera setups. Experimental results demonstrate that our approach consistently improves rendering quality and semantic segmentation performance, outperforming baseline methods based on random selection and uncertainty-based heuristics.

Yiqian Li, Wen Jiang, Kostas Daniilidis• 2025

Related benchmarks

TaskDatasetResultRank
Dynamic and Semantic 3DGS Active TrainingNeu3D average across five dynamic scenes
SSIM0.9239
10
Dynamic and semantic 3DGSNeu3D average across five dynamic scenes
SSIM0.9239
4
Static Semantic 3D Gaussian SplattingReplica Average
SSIM96.26
4
Showing 3 of 3 rows

Other info

Follow for update