ROI-GS: Interest-based Local Quality 3D Gaussian Splatting
This addresses the problem of limited fine detail on objects of interest in 3D Gaussian Splatting for 3D scene reconstruction, representing an incremental improvement.
The paper tackles the challenge of efficiently reconstructing 3D scenes with high detail on objects of interest by proposing ROI-GS, an object-aware framework that improves local quality by up to 2.96 dB PSNR, reduces model size by about 17%, and achieves faster training compared to baseline methods.
We tackle the challenge of efficiently reconstructing 3D scenes with high detail on objects of interest. Existing 3D Gaussian Splatting (3DGS) methods allocate resources uniformly across the scene, limiting fine detail to Regions Of Interest (ROIs) and leading to inflated model size. We propose ROI-GS, an object-aware framework that enhances local details through object-guided camera selection, targeted Object training, and seamless integration of high-fidelity object of interest reconstructions into the global scene. Our method prioritizes higher resolution details on chosen objects while maintaining real-time performance. Experiments show that ROI-GS significantly improves local quality (up to 2.96 dB PSNR), while reducing overall model size by $\approx 17\%$ of baseline and achieving faster training for a scene with a single object of interest, outperforming existing methods.