The use of point clouds is becoming increasingly popular. We present a general framework for performing geometry filtering on point-based surface through applying the meshless local Petrol-Galelkin （MLPG） to obtain ...The use of point clouds is becoming increasingly popular. We present a general framework for performing geometry filtering on point-based surface through applying the meshless local Petrol-Galelkin （MLPG） to obtain the solution of a screened Poisson equation. The enhancement or smoothing of surfaces is controlled by a gradient scale parameter. Anisotropic filtering is supported by the adapted Riemannian metric. Contrary to the other approaches of partial differential equation for point-based surface, the proposed approach neither needs to construct local or global triangular meshes, nor needs global parameterization. It is only based on the local tangent space and local interpolated surfaces. Experiments demonstrate the efficiency of our approach.展开更多
Gradient-domain rendering estimates finite difference gradients of image intensities and reconstructs the final result by solving a screened Poisson problem,which shows improvements over merely sampling pixel intensit...Gradient-domain rendering estimates finite difference gradients of image intensities and reconstructs the final result by solving a screened Poisson problem,which shows improvements over merely sampling pixel intensities.Adaptive sampling is another orthogonal research area that focuses on distributing samples adaptively in the primal domain.However,adaptive sampling in the gradient domain with low sampling budget has been less explored.Our idea is based on the observation that signals in the gradient domain are sparse,which provides more flexibility for adaptive sampling.We propose a deep-learning-based end-to-end sampling and reconstruction framework in gradient-domain rendering,enabling adaptive sampling gradient and the primal maps simultaneously.We conducted extensive experiments for evaluation and showed that our method produces better reconstruction quality than other methods in the test dataset.展开更多
Gradient-domain rendering methods can render higher-quality images at the same time cost compared with traditional ray tracing rendering methods, and, combined with the neural network, achieve better rendering quality...Gradient-domain rendering methods can render higher-quality images at the same time cost compared with traditional ray tracing rendering methods, and, combined with the neural network, achieve better rendering quality than conventional screened Poisson reconstruction. However, it is still challenging for these methods to keep detailed information, especially in areas with complex indirect illumination and shadows. We propose an unsupervised reconstruction method that separates the direct rendering from the indirect, and feeds them into our unsupervised network with some corresponding auxiliary channels as two separated tasks. In addition, we introduce attention modules into our network which can further improve details. We finally combine the results of the direct and indirect illumination tasks to form the rendering results. Experiments show that our method significantly improves image quality details, especially in scenes with complex conditions.展开更多
基金This work is partly supported by the National Natural Science Foundation of China under Grant Nos. 61772097 and U1401252, and Scientific and Technological Research Program of Chongqing Municipal Education Commission of China under Grant No. KJ1400429.
文摘The use of point clouds is becoming increasingly popular. We present a general framework for performing geometry filtering on point-based surface through applying the meshless local Petrol-Galelkin （MLPG） to obtain the solution of a screened Poisson equation. The enhancement or smoothing of surfaces is controlled by a gradient scale parameter. Anisotropic filtering is supported by the adapted Riemannian metric. Contrary to the other approaches of partial differential equation for point-based surface, the proposed approach neither needs to construct local or global triangular meshes, nor needs global parameterization. It is only based on the local tangent space and local interpolated surfaces. Experiments demonstrate the efficiency of our approach.
基金supported by the Key R&D Program of Zhejiang Province(No.2023C01039).
文摘Gradient-domain rendering estimates finite difference gradients of image intensities and reconstructs the final result by solving a screened Poisson problem,which shows improvements over merely sampling pixel intensities.Adaptive sampling is another orthogonal research area that focuses on distributing samples adaptively in the primal domain.However,adaptive sampling in the gradient domain with low sampling budget has been less explored.Our idea is based on the observation that signals in the gradient domain are sparse,which provides more flexibility for adaptive sampling.We propose a deep-learning-based end-to-end sampling and reconstruction framework in gradient-domain rendering,enabling adaptive sampling gradient and the primal maps simultaneously.We conducted extensive experiments for evaluation and showed that our method produces better reconstruction quality than other methods in the test dataset.
基金supported by the National Key Research and Development Program of China under Grant No.2020YFB1708900the National Natural Science Foundation of China under Grant No.62272275.
文摘Gradient-domain rendering methods can render higher-quality images at the same time cost compared with traditional ray tracing rendering methods, and, combined with the neural network, achieve better rendering quality than conventional screened Poisson reconstruction. However, it is still challenging for these methods to keep detailed information, especially in areas with complex indirect illumination and shadows. We propose an unsupervised reconstruction method that separates the direct rendering from the indirect, and feeds them into our unsupervised network with some corresponding auxiliary channels as two separated tasks. In addition, we introduce attention modules into our network which can further improve details. We finally combine the results of the direct and indirect illumination tasks to form the rendering results. Experiments show that our method significantly improves image quality details, especially in scenes with complex conditions.
