-
公开(公告)号：US11948306B2
公开(公告)日：2024-04-02
申请号：US17497285
申请日：2021-10-08
CPC分类号： G06T7/12 , G06N3/08 , G06T7/0012 , G16H30/20 , G06T2207/20081 , G06T2207/20084 , G06T2207/30101
摘要： At least one input image comprising curvilinear features is received. Latent representations of the input images are learned using a trained deep neural network. At least one boundary estimate is determined based on the latent representations. At least one segmentation estimate of the at least one input image is determined based on the latent representations. The at least one image is mapped to output segmentation maps based on the segmentation estimate and the at least one boundary estimate.
-
公开(公告)号：US11645770B2
公开(公告)日：2023-05-09
申请号：US17529012
申请日：2021-11-17
IPC分类号： G06T7/44 , G06T7/00 , G06N20/00 , B29C64/393 , B29C64/35 , B29C64/209 , G06T7/136
CPC分类号： G06T7/44 , B29C64/209 , B29C64/35 , B29C64/393 , G06N20/00 , G06T7/0008 , G06T7/136
摘要： One embodiment can provide a system for detecting occlusion at an orifice of a three-dimensional (3D) printer nozzle while the printer nozzle is jetting liquid droplets. During operation, the system uses one or more cameras to capture an image of the orifice of the printer nozzle while the 3D printer nozzle is jetting liquid droplets. The system performs an image-analysis operation on the captured image to identify occluded regions within the orifice of the 3D printer nozzle, compute an occlusion fraction based on the determined occluded regions, and generate an output based on the computed occlusion fraction, thereby facilitating effective maintenance of the 3D printer.
-
公开(公告)号：US20230005108A1
公开(公告)日：2023-01-05
申请号：US17363293
申请日：2021-06-30
摘要： To replace text in a digital video image sequence, a system will process frames of the sequence to: define a region of interest (ROI) with original text in each of the frames; use the ROIs to select a reference frame from the sequence; select a target frame from the sequence; determine a transform function between the ROI of the reference frame and the ROI of the target frame; replace the original text in the ROI of the reference frame with replacement text to yield a modified reference frame ROI; and use the transform function to transform the modified reference frame ROI to a modified target frame ROI in which the original text is replaced with the replacement text. The system will then insert the modified target frame ROI into the target frame to produce a modified target frame. This process may repeat for other target frames of the sequence.
-
14.发明授权公开(公告)号：US11537277B2
公开(公告)日：2022-12-27
申请号：US16040220
申请日：2018-07-19
IPC分类号： G06F3/04845 , G06T7/11 , G06F3/04847 , G06N3/08 , G06T5/00 , G06T11/00 , G06N3/04 , G06T7/143 , G06T7/35
摘要： Embodiments described herein provide a system for generating semantically accurate synthetic images. During operation, the system generates a first synthetic image using a first artificial intelligence (AI) model and presents the first synthetic image in a user interface. The user interface allows a user to identify image units of the first synthetic image that are semantically irregular. The system then obtains semantic information for the semantically irregular image units from the user via the user interface and generates a second synthetic image using a second AI model based on the semantic information. The second synthetic image can be an improved image compared to the first synthetic image.
-
公开(公告)号：US11508169B2
公开(公告)日：2022-11-22
申请号：US16737702
申请日：2020-01-08
发明人： Raja Bala , Robert R. Price , Edo Collins
IPC分类号： G06T11/60 , G06V30/262 , G06F17/16 , G06K9/62
摘要： Embodiments described herein provide a system for generating synthetic images with localized editing. During operation, the system obtains a source image and a target image for image synthesis and selects a semantic element from the source image. The semantic element indicates a semantically meaningful part of an object depicted in the source image. The system then determines the style information associated with the source and target images. Subsequently, the system generates a synthetic image by transferring the style of the semantic element from the source image to the target image based on the feature representations. In this way, the system can facilitate localized editing of the target image.
-
公开(公告)号：US11423597B2
公开(公告)日：2022-08-23
申请号：US17123841
申请日：2020-12-16
摘要： Methods of removing text from digital video or still images are disclosed. An image processing system receives an input image set defining a region of interest (ROI) that contains text. The system determines an input background color for the ROI. The system applies a text infilling function to remove text from the ROI to yield a preliminary output image set. The system may determine a residual corrective signal that corresponds to a measurement of background color error between the input set and the preliminary output set. The system may apply the residual corrective signal to the ROI in the preliminary output set to yield a final output set that does not contain the text. Alternatively, the system may remove background from the ROI of the input set before text infilling, then return background to the ROI after the text infilling.
-
公开(公告)号：US11270123B2
公开(公告)日：2022-03-08
申请号：US17026897
申请日：2020-09-21
发明人： Karunakaran Sureshkumar , Raja Bala
IPC分类号： H04N7/10 , G06K9/00 , G06K9/62 , G10L15/04 , G10L15/18 , G10L15/22 , G10L21/0272 , G10L25/63 , H04N21/439 , H04N21/44 , H04N21/81
摘要： Embodiments described herein provide a system for localized contextual video annotation. During operation, the system can segment a video into a plurality of segments based on a segmentation unit and parse a respective segment for generating multiple input modalities for the segment. A respective input modality can indicate a form of content in the segment. The system can then classify the segment into a set of semantic classes based on the input modalities and determine an annotation for the segment based on the set of semantic classes.
-
公开(公告)号：US11068746B2
公开(公告)日：2021-07-20
申请号：US16235697
申请日：2018-12-28
发明人： Raja Bala , Matthew Shreve , Jeyasri Subramanian , Pei Li
摘要： A method for predicting the realism of an object within an image includes generating a training image set for a predetermined object type. The training image set comprises one or more training images at least partially generated using a computer. A pixel level training spatial realism map is generated for each training image of the one or more training images. Each training spatial realism map configured to represent a perceptual realism of the corresponding training image. A predictor is trained using the training image set and the corresponding training spatial realism maps. An image of the predetermined object is received. A spatial realism map of the received image is produced using the trained predictor.
-
公开(公告)号：US20210117685A1
公开(公告)日：2021-04-22
申请号：US17026897
申请日：2020-09-21
发明人： Karunakaran Sureshkumar , Raja Bala
IPC分类号： G06K9/00 , G06K9/62 , H04N21/44 , H04N21/439 , H04N21/81 , G10L25/63 , G10L21/0272 , G10L15/22 , G10L15/18 , G10L15/04
摘要： Embodiments described herein provide a system for localized contextual video annotation. During operation, the system can segment a video into a plurality of segments based on a segmentation unit and parse a respective segment for generating multiple input modalities for the segment. A respective input modality can indicate a form of content in the segment. The system can then classify the segment into a set of semantic classes based on the input modalities and determine an annotation for the segment based on the set of semantic classes.
-
公开(公告)号：US10832413B2
公开(公告)日：2020-11-10
申请号：US16223519
申请日：2018-12-18
摘要： A method for curvilinear object segmentation includes receiving at least one input image comprising curvilinear features. The at least one input image is mapped to segmentation maps of the curvilinear features using a deep network having a representation module and a task module. The mapping includes transforming the input image in the representation module using learnable filters configured to balance recognition of curvilinear geometry with reduction of training error. The segmentation maps are produced using the transformed input image in the task module.
-
-
-
-
-
-
-
-
-
搜索结果
126 条记录 (耗时 0.037 秒)
