ODIUM
发表于 2025-3-25 06:19:52
http://reply.papertrans.cn/24/2343/234257/234257_21.png
落叶剂
发表于 2025-3-25 11:21:31
,Deep Fourier-Based Exposure Correction Network with Spatial-Frequency Interaction,n (SFI) block in two formats tailored to these two sub-networks, which interactively process the local spatial features and the global frequency information to encourage the complementary learning. Extensive experiments demonstrate that our method achieves superior results than other approaches with
藐视
发表于 2025-3-25 14:01:05
,Frequency and Spatial Dual Guidance for Image Dehazing,al domain. Extensive experiments on synthetic and real-world datasets demonstrate that our method outperforms the state-of-the-art approaches both visually and quantitatively. Our code is released publicly at ..
Hallowed
发表于 2025-3-25 16:49:18
,Learning Discriminative Shrinkage Deep Networks for Image Deconvolution,rties of the Maxout function and develop a deep CNN model with Maxout layers to learn discriminative shrinkage functions, which directly approximates the solutions of these two sub-problems. Moreover, the fast-Fourier-transform-based image restoration usually leads to ringing artifacts. At the same
爱好
发表于 2025-3-25 23:05:08
,KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution,ear physical patterns and the mutually iterative process between blur kernel and HR image can soundly guide the KXNet to be evolved in the right direction. Extensive experiments on synthetic and real data finely demonstrate the superior accuracy and generality of our method beyond the current repres
hermetic
发表于 2025-3-26 02:20:54
ARM: Any-Time Super-Resolution Method, computation-performance tradeoff. Moreover, each SISR subnet shares weights of the ARM supernet, thus no extra parameters are introduced. The setting of multiple subnets can well adapt the computational cost of SISR model to the dynamically available hardware resources, allowing the SISR task to be
venous-leak
发表于 2025-3-26 05:01:14
http://reply.papertrans.cn/24/2343/234257/234257_27.png
DUST
发表于 2025-3-26 12:25:33
,RealFlow: EM-Based Realistic Optical Flow Dataset Generation from Videos,bi-directional hole filling techniques to alleviate the artifacts of the image synthesis. In the E-step, RIPR renders new images to create a large quantity of training data. In the M-step, we utilize the generated training data to train an optical flow network, which can be used to estimate optical
geometrician
发表于 2025-3-26 15:33:11
http://reply.papertrans.cn/24/2343/234257/234257_29.png
使更活跃
发表于 2025-3-26 18:02:43
http://reply.papertrans.cn/24/2343/234257/234257_30.png