3 papers
cs.CV2025
2DGS-R: Revisiting the Normal Consistency Regularization in 2D Gaussian Splatting
Haofan Ren, Qingsong Yan, Ming Lu +2
Recent advancements in 3D Gaussian Splatting (3DGS) have greatly influenced neural fields, as it enables high-fidelity rendering with impressive visual quality. However, 3DGS has d…
cs.CV2025
K-Buffers: A Plug-in Method for Enhancing Neural Fields with Multiple Buffers
Haofan Ren, Zunjie Zhu, Xiang Chen +3
Neural fields are now the central focus of research in 3D vision and computer graphics. Existing methods mainly focus on various scene representations, such as neural points and 3D…
cs.CV2025
VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control
Lifeng Lin, Rongfeng Lu, Quan Chen +5
Sparse-view 3D reconstruction is a fundamental yet challenging task in practical 3D reconstruction applications. Recently, many methods based on the 3D Gaussian Splatting (3DGS) fr…