Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304083162> ?p ?o ?g. }
- W4304083162 abstract "Image deraining is an important task for subsequent multimedia applications in rainy weather. Traditional deep learning-based methods rely on the quantity and diversity of training data, which is hard to cover all complex real-world rain scenarios. In this work, we propose the first Unsupervised Controllable Network (UConNet) to flexibly tackle different rain scenarios by adaptively controlling the network at the inference stage. Specifically, our unsupervised network takes the physics-based regularizations as the unsupervised loss function. Then, we sensibly derive the relationship between trade-off parameters of the loss function and the weightings of feature maps. Based on this relationship, our learned UConNet can be flexibly customized for different rain scenarios by controlling the weightings of feature maps at the inference stage. Alternatively, these weightings can also be efficiently determined by a learned weightings recommendation network. Extensive experiments for image and video deraining show that our method achieves very promising effectiveness, efficiency, and generalization abilities as compared with state-of-the-art methods." @default.
- W4304083162 created "2022-10-10" @default.
- W4304083162 creator A5011715660 @default.
- W4304083162 creator A5036399063 @default.
- W4304083162 creator A5037421955 @default.
- W4304083162 creator A5037663174 @default.
- W4304083162 creator A5073610409 @default.
- W4304083162 date "2022-10-10" @default.
- W4304083162 modified "2023-09-27" @default.
- W4304083162 title "UConNet: Unsupervised Controllable Network for Image and Video Deraining" @default.
- W4304083162 cites W1909316225 @default.
- W4304083162 cites W2121396509 @default.
- W4304083162 cites W2154621477 @default.
- W4304083162 cites W2209874411 @default.
- W4304083162 cites W2509784253 @default.
- W4304083162 cites W2559264300 @default.
- W4304083162 cites W2777170053 @default.
- W4304083162 cites W2778532031 @default.
- W4304083162 cites W2789288870 @default.
- W4304083162 cites W2790883954 @default.
- W4304083162 cites W2884068670 @default.
- W4304083162 cites W2888632407 @default.
- W4304083162 cites W2910832120 @default.
- W4304083162 cites W2913360047 @default.
- W4304083162 cites W2963152299 @default.
- W4304083162 cites W2963800716 @default.
- W4304083162 cites W2963843230 @default.
- W4304083162 cites W2963878020 @default.
- W4304083162 cites W2964267765 @default.
- W4304083162 cites W2981380309 @default.
- W4304083162 cites W2981813535 @default.
- W4304083162 cites W2991350899 @default.
- W4304083162 cites W3022210053 @default.
- W4304083162 cites W3026432413 @default.
- W4304083162 cites W3028045870 @default.
- W4304083162 cites W3035250394 @default.
- W4304083162 cites W3035326127 @default.
- W4304083162 cites W3035688623 @default.
- W4304083162 cites W3047572483 @default.
- W4304083162 cites W3083885798 @default.
- W4304083162 cites W3093101131 @default.
- W4304083162 cites W3093244203 @default.
- W4304083162 cites W3108352987 @default.
- W4304083162 cites W3114544597 @default.
- W4304083162 cites W3118482223 @default.
- W4304083162 cites W3158248812 @default.
- W4304083162 cites W3167082280 @default.
- W4304083162 cites W3169078099 @default.
- W4304083162 cites W3171125843 @default.
- W4304083162 cites W3177905498 @default.
- W4304083162 cites W3183026600 @default.
- W4304083162 cites W3186182384 @default.
- W4304083162 cites W3200683480 @default.
- W4304083162 cites W3205396612 @default.
- W4304083162 doi "https://doi.org/10.1145/3503161.3547772" @default.
- W4304083162 hasPublicationYear "2022" @default.
- W4304083162 type Work @default.
- W4304083162 citedByCount "0" @default.
- W4304083162 crossrefType "proceedings-article" @default.
- W4304083162 hasAuthorship W4304083162A5011715660 @default.
- W4304083162 hasAuthorship W4304083162A5036399063 @default.
- W4304083162 hasAuthorship W4304083162A5037421955 @default.
- W4304083162 hasAuthorship W4304083162A5037663174 @default.
- W4304083162 hasAuthorship W4304083162A5073610409 @default.
- W4304083162 hasConcept C115961682 @default.
- W4304083162 hasConcept C119857082 @default.
- W4304083162 hasConcept C124101348 @default.
- W4304083162 hasConcept C127413603 @default.
- W4304083162 hasConcept C134306372 @default.
- W4304083162 hasConcept C138885662 @default.
- W4304083162 hasConcept C14036430 @default.
- W4304083162 hasConcept C153180895 @default.
- W4304083162 hasConcept C154945302 @default.
- W4304083162 hasConcept C177148314 @default.
- W4304083162 hasConcept C201995342 @default.
- W4304083162 hasConcept C2776214188 @default.
- W4304083162 hasConcept C2776401178 @default.
- W4304083162 hasConcept C2780428219 @default.
- W4304083162 hasConcept C2780451532 @default.
- W4304083162 hasConcept C33923547 @default.
- W4304083162 hasConcept C41008148 @default.
- W4304083162 hasConcept C41895202 @default.
- W4304083162 hasConcept C50644808 @default.
- W4304083162 hasConcept C52622490 @default.
- W4304083162 hasConcept C78458016 @default.
- W4304083162 hasConcept C78519656 @default.
- W4304083162 hasConcept C8038995 @default.
- W4304083162 hasConcept C86803240 @default.
- W4304083162 hasConceptScore W4304083162C115961682 @default.
- W4304083162 hasConceptScore W4304083162C119857082 @default.
- W4304083162 hasConceptScore W4304083162C124101348 @default.
- W4304083162 hasConceptScore W4304083162C127413603 @default.
- W4304083162 hasConceptScore W4304083162C134306372 @default.
- W4304083162 hasConceptScore W4304083162C138885662 @default.
- W4304083162 hasConceptScore W4304083162C14036430 @default.
- W4304083162 hasConceptScore W4304083162C153180895 @default.
- W4304083162 hasConceptScore W4304083162C154945302 @default.
- W4304083162 hasConceptScore W4304083162C177148314 @default.
- W4304083162 hasConceptScore W4304083162C201995342 @default.
- W4304083162 hasConceptScore W4304083162C2776214188 @default.