Object-Centric 2D Gaussian Splatting: Background Removal and Occlusion-Aware Pruning for Compact Object Models
This work addresses the need for compact and efficient object models in computer vision, enabling downstream applications like appearance editing and physics simulation, though it is incremental as it builds on existing Gaussian Splatting techniques.
The paper tackles the problem of Gaussian Splatting methods being computationally expensive and unsuitable for object-specific applications by proposing an object-centric approach with occlusion-aware pruning, resulting in models that are up to 96% smaller and 71% faster to train while maintaining competitive quality.
Current Gaussian Splatting approaches are effective for reconstructing entire scenes but lack the option to target specific objects, making them computationally expensive and unsuitable for object-specific applications. We propose a novel approach that leverages object masks to enable targeted reconstruction, resulting in object-centric models. Additionally, we introduce an occlusion-aware pruning strategy to minimize the number of Gaussians without compromising quality. Our method reconstructs compact object models, yielding object-centric Gaussian and mesh representations that are up to 96% smaller and up to 71% faster to train compared to the baseline while retaining competitive quality. These representations are immediately usable for downstream applications such as appearance editing and physics simulation without additional processing.