Next Best View Selections for Semantic and Dynamic 3D Gaussian Splatting
By: Yiqian Li, Wen Jiang, Kostas Daniilidis
Potential Business Impact:
Chooses best camera views to train robots.
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.
Similar Papers
Online 3D Gaussian Splatting Modeling with Novel View Selection
CV and Pattern Recognition
Creates more complete 3D models from fewer pictures.
Online 3D Gaussian Splatting Modeling with Novel View Selection
CV and Pattern Recognition
Makes 3D pictures more complete from videos.
IntelliCap: Intelligent Guidance for Consistent View Sampling
CV and Pattern Recognition
Guides cameras to take perfect pictures for 3D scenes.