OP2GS: Object-Aware 3D Gaussian Splatting with Dual-Opacity Primitives

TL;DR

OP2GS introduces an object-aware 3D Gaussian representation with dual opacity primitives, enabling efficient scene understanding and open-vocabulary tasks by decoupling visual reconstruction from object instance labeling.

Contribution

It proposes a novel dual-opacity formulation for 3D Gaussian primitives, improving object-level identity and reducing computational overhead in scene representation.

Findings

Achieves competitive open-vocabulary performance.

Reduces computational overhead compared to feature-based methods.

Effectively models object masks with dual-opacity primitives.

Abstract

3D Gaussian Splatting (3DGS) provides an explicit and efficient scene representation, but its primitives lack inherent object-level identity, hindering downstream tasks such as open-vocabulary scene understanding. Existing methods typically address this by either distilling high-dimensional feature embeddings into Gaussians or by lifting 2D mask labels into 3D via heuristic refinement. However, feature-based approaches incur heavy storage and decoding overhead, while lifting-based pipelines remain vulnerable to label contamination: Gaussians necessary for appearance reconstruction often receive incorrect object labels during 2D-to-3D projection. We propose OP2GS, an object-aware Gaussian representation that augments each primitive with an explicit instance identity and a dedicated instance opacity $\sigma^{*}$ for object-mask rendering. The original opacity $\sigma$ remains responsible for visual reconstruction, while $\sigma^{*}$ models whether a Gaussian should contribute to a particular object mask. This dual-opacity formulation decouples visual existence from instance occupancy: mislabeled Gaussians can remain available for image rendering while becoming transparent in the object-mask branch. To learn this representation, we introduce a random object loss that optimizes the 1D instance occupancy field using the standard transmittance-based visibility of 3DGS. Semantic descriptors are then attached at the object level through multi-view aggregation, eliminating per-Gaussian feature storage. Compared with feature-training approaches, OP2GS achieves competitive open-vocabulary performance while significantly reducing computational overhead. Compared with training-free pipelines, it leverages physically consistent occupancy learning to resolve visibility ambiguities.