OccamView: Object-Conditioned View Selection for Frame-Budgeted Active 3D Gaussian Reconstruction

2026-08-17

AI Summary

This study addresses the challenge of incomplete object observation in active 3D Gaussian reconstruction under constrained frame budgets by proposing an object-conditioned view selection framework. The method integrates online object memory with occlusion-aware scoring and introduces a novel Geo-Floor mechanism alongside an object-conditioned reranking strategy to effectively balance geometric exploration and target completion. Experimental evaluations on the Replica and Matterport3D datasets demonstrate that this framework significantly reduces completion error while improving completion rates. These results validate the effectiveness of the proposed approach in achieving high-quality object-level reconstruction within limited computational resources, offering a robust solution for resource-constrained active perception tasks.

Abstract

Active 3D Gaussian reconstruction fundamentally relies on selecting informative next-best views under limited sensing budgets. Existing active 3DGS methods primarily plan viewpoints according to geometric information gain, treating object-induced hidden regions in the same manner as general unexplored space. Under tight frame budgets, such geometry-driven strategies may prioritize global scene coverage while leaving partially observed objects incompletely reconstructed. To address this limitation, we propose OccamView, an object-conditioned view-selection framework for frame-budgeted active 3D Gaussian reconstruction. Rather than predicting unseen object geometry or performing shape completion, OccamView maintains an online object memory from open-vocabulary detections grounded in measured RGB-D observations and represents unresolved local occupancy around detected objects as conservative hidden-region proxies. Candidate viewpoints are then evaluated using an occlusion-aware proxy-coverage score. Furthermore, we introduce a Geo-Floor mechanism that restricts object-conditioned re-ranking to geometrically competitive candidates, allowing object-conditioned cues to guide complementary observations while preserving the geometry-driven exploration behavior of the underlying planner. Experiments on Replica and Matterport3D under a unified frame-budgeted protocol show that OccamView consistently reduces Completion and improves Completion Ratio across five frame budgets, with particularly pronounced gains under limited frame budgets. These results demonstrate that lightweight object-conditioned cues effectively complement geometry-driven active view planning.

Problem

• Active 3D Gaussian Reconstruction
• Frame-Budgeted View Selection
• Object-Conditioned Planning
• Incomplete Object Reconstruction

Innovation

• Object-Conditioned View Selection
• Active 3D Gaussian Reconstruction
• Hidden-Region Proxies
• Occlusion-Aware Proxy-Coverage Score
• Geo-Floor Mechanism