去世 发表于 2025-3-26 21:57:59
Multi-modality Image Registration Models and Efficient Algorithms,l to generate a diffeomorphic transformation. The idea is illustrated by using a particular model based on reformulated normalized gradients of the images as the fidelity term and higher-order derivatives as the regularizer. By adding a control term motivated by quasi-conformal maps and Beltrami coeHyperopia 发表于 2025-3-27 02:51:56
Fast Algorithms for Surface Reconstruction from Point Cloud,y in . An approach using Semi-Implicit Method (SIM) improves the computational efficiency through relaxation on the time-step constraint. An approach based on Augmented Lagrangian Method (ALM) reduces the run-time viamisanthrope 发表于 2025-3-27 07:44:37
A Total Variation Regularization Method for Inverse Source Problem with Uniform Noise,tate function which is corrupted by uniform noise. Under the framework of maximum a posteriori estimator, the problem can be converted into an optimization problem where the objective function is composed of an . norm and a total variation (TV) regularization term. By introducing an auxiliary variabWAX 发表于 2025-3-27 09:40:17
http://reply.papertrans.cn/63/6263/626262/626262_34.pngreserve 发表于 2025-3-27 17:15:24
http://reply.papertrans.cn/63/6263/626262/626262_35.pngdilute 发表于 2025-3-27 18:52:05
On the Optimal Proximal Parameter of an ADMM-like Splitting Method for Separable Convex Programmingfunctions. Its proximal parameter is required to be sufficiently large to theoretically ensure the convergence, despite that a smaller value of this parameter is preferred for numerical acceleration. Empirically, this method has been applied to solve various applications with relaxed restrictions onLITHE 发表于 2025-3-28 01:26:09
A New Initialization Method for Neural Networks with Weight Sharing, is later generalized to Kaiming initialization by He, Zhang, Ren and Sun are now widely used. However, from experiments we find that networks with heavy weight sharing are difficulty to train even with the Xavier or the Kaiming initialization. We also notice that a certain simple network can be dechysterectomy 发表于 2025-3-28 04:39:34
The Shortest Path AMID 3-D Polyhedral Obstacles,ent algorithm to find the globally shortest path by solving stochastic differential equations (SDEs). The main idea is based on the simple structure of the shortest path, namely it consists of straight line segments connected by junctions on the edges of the polyhedral obstacles. Thus, finding the semulsify 发表于 2025-3-28 06:29:11
http://reply.papertrans.cn/63/6263/626262/626262_39.png防止 发表于 2025-3-28 10:57:21
http://reply.papertrans.cn/63/6263/626262/626262_40.png