Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

4 results about "Cross processing" patented technology

Cross processing (sometimes abbreviated to Xpro) is the deliberate processing of photographic film in a chemical solution intended for a different type of film. The effect was discovered independently by many different photographers often by mistake in the days of C-22 and E-4. Color cross processed photographs are often characterized by unnatural colors and high contrast. The results of cross processing differ from case to case, as the results are determined by many factors such as the make and type of the film used, the amount of light exposed onto the film and the chemical used to develop the film. Similar effects can also be achieved with digital filter effects.

Photovoltaic power generation power short-term prediction method, device, equipment and medium

The invention relates to the technical field of power generation prediction, and provides a photovoltaic power generation power short-term prediction method, device, equipment and medium, and the method comprises the steps: obtaining multi-modal data for a to-be-predicted photovoltaic power station, the multi-modal data being data describing the operation condition of the to-be-predicted photovoltaic power station, power station equipment and the environment of the to-be-predicted photovoltaic power station; generating power feature extraction and meteorological feature extraction are carried out according to the multi-modal data, and fusion processing is carried out on the extracted features to generate a fusion feature vector; performing explicit feature cross processing on the fusion feature vector to generate an attenuation coefficient; calculating clear sky power based on a clear sky model according to the multi-modal data; and according to the attenuation coefficient and the clear sky power, calculating a photovoltaic generation power prediction value of the photovoltaic power station to be predicted. According to the method, deep feature extraction and fusion are carried out on the multi-modal data, and the attenuation coefficient driven by the data is combined with the clear sky model based on the physical law, so that the prediction precision is remarkably improved.
Owner:CHINA RESOURCES POWER (HUBEI) SALES CO LTD

Image processing methods and training methods for stable diffusion models of graph-generated images

This application relates to the field of image processing technology, providing an image processing method and a training method for a stable diffusion model of an image-generated image. The stable diffusion model of the image-generated image includes an image cross-attention mechanism layer. The method includes: inputting a first image with a first illumination effect and a target ambient light image into the trained stable diffusion model of the image-generated image; the stable diffusion model of the image-generated image performs cross-processing between the first image and the target ambient light image through the image cross-attention mechanism layer, enabling the stable diffusion model of the image-generated image to re-illuminate the first image under the guidance of the target ambient light image, outputting a second image with a second illumination effect. This achieves the reconstruction of the image illumination effect, improves the image illumination effect, and enhances image quality and image effect.
Owner:HONOR DEVICE CO LTD

Lineup generation method and device, storage medium and electronic device

PendingCN122346822AExcavation is accurate and efficientImprove experienceAlgorithmEngineering
The application discloses a lineup generation method and device, a storage medium and an electronic device. The method comprises the following steps: performing cross processing on an initial lineup set and a candidate lineup set to form a plurality of lineup pairs containing a first lineup and a second lineup from the two sets respectively. The lineup pairs are sequentially input into a target win rate prediction model with a cross network to determine the predicted fitness corresponding to each first lineup. The adaptive crossover probability and the adaptive mutation probability are calculated according to the predicted fitness, the initial lineup set is updated according to the two probabilities, and the iteration is continuously performed until the iteration number meets the preset condition, the target head lineup is determined, and the technical effects of improving the prediction accuracy and the mining efficiency are realized. The application solves the technical problems of poor evaluation reliability, poor generalization effect, low prediction lineup strength precision and low process efficiency of output head lineup result of the lineup strength model in the related art.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD