SVR-GS: Spatially Variant Regularization for Probabilistic Masks in 3D Gaussian Splatting
3D Gaussian Splatting (3DGS) enables fast, high-quality novel view synthesis but typically relies on densification followed by pruning to optimize the number of Gaussians. Existing mask-based pruning, such as MaskGS, regularizes the global mean of the mask, which is misaligned with the local per-pixel (per-ray) reconstruction loss that determines image quality along individual camera rays. This paper introduces SVR-GS, a spatially variant regularizer that renders a per-pixel spatial mask from each Gaussian's effective contribution along the ray, thereby applying sparsity pressure where it matters: on low-importance Gaussians. We explore three spatial-mask aggregation strategies, implement them in CUDA, and conduct a gradient analysis to motivate our final design. Extensive experiments on Tanks\&Temples, Deep Blending, and Mip-NeRF360 datasets demonstrate that, on average across the three datasets, the proposed SVR-GS reduces the number of Gaussians by 1.79\(\times\) compared to MaskGS and 5.63\(\times\) compared to 3DGS, while incurring only 0.50 dB and 0.40 dB PSNR drops, respectively. These gains translate into significantly smaller, faster, and more memory-efficient models, making them well-suited for real-time applications such as robotics, AR/VR, and mobile perception.
Code (0)
등록된 구현이 없습니다.
Tasks
Novel View SynthesisSimilar Papers 제목 키워드 기반
Unsupervised learning of spatially varying regularization for diffeomorphic image registration
Spatially varying regularization accommodates the deformation variations that may be necessary for different anatomical regions during deformable image registration. Historically, optimization-based registration models h…
Bayesian OptimizationImage RegistrationConditional Deformable Image Registration with Spatially-Variant and Adaptive Regularization
Deep learning-based image registration approaches have shown competitive performance and run-time advantages compared to conventional image registration methods. However, existing learning-based approaches mostly require…
Hyperparameter OptimizationImage RegistrationSemDynReg: Semantics-Guided Deformation Regularization for Dynamic 3D Gaussian Splatting
Deformable 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for rendering dynamic scenes in a wide range of 3D applications. However, existing deformation field-based approaches largely lack explicit obj…
Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring
The classical maximum a-posteriori (MAP) framework for non-blind image deblurring requires defining suitable data and regularization terms, whose interplay yields the desired clear image through optimization. The vas…
Blind Image DeblurringDeblurringImage DeblurringEndoGS: Deformable Endoscopic Tissues Reconstruction with Gaussian Splatting
Surgical 3D reconstruction is a critical area of research in robotic surgery, with recent works adopting variants of dynamic radiance fields to achieve success in 3D reconstruction of deformable tissues from single-viewp…
3D Reconstruction