-
公开(公告)号:US20160124995A1
公开(公告)日:2016-05-05
申请号:US14994459
申请日:2016-01-13
Applicant: eBay Inc.
Inventor: Anurag Bhardwaj , Mohammad Haris Baig , Robinson Piramuthu , Vignesh Jagadeesh , Wei Di
CPC classification number: G06T7/50 , G06F17/3025 , G06F17/30256 , G06F17/30262 , G06F17/30277 , G06K9/00208 , G06K9/4609 , G06T7/194 , G06T7/62 , G06T2207/10024 , G06T2207/10028 , G06T2207/20081
Abstract: During a training phase, a machine accesses reference images with corresponding depth information. The machine calculates visual descriptors and corresponding depth descriptors from this information. The machine then generates a mapping that correlates these visual descriptors with their corresponding depth descriptors. After the training phase, the machine may perform depth estimation based on a single query image devoid of depth information. The machine may calculate one or more visual descriptors from the single query image and obtain a corresponding depth descriptor for each visual descriptor from the generated mapping. Based on obtained depth descriptors, the machine creates depth information that corresponds to the submitted single query image.
-
公开(公告)号:US09275078B2
公开(公告)日:2016-03-01
申请号:US14288233
申请日:2014-05-27
Applicant: eBay Inc.
Inventor: Anurag Bhardwaj , Mohammad Haris Baig , Robinson Piramuthu , Vignesh Jagadeesh , Wei Di
IPC: G06F17/30
CPC classification number: G06T7/50 , G06F17/3025 , G06F17/30256 , G06F17/30262 , G06F17/30277 , G06K9/00208 , G06K9/4609 , G06T7/194 , G06T7/62 , G06T2207/10024 , G06T2207/10028 , G06T2207/20081
Abstract: During a training phase, a machine accesses reference images with corresponding depth information. The machine calculates visual descriptors and corresponding depth descriptors from this information. The machine then generates a mapping that correlates these visual descriptors with their corresponding depth descriptors. After the training phase, the machine may perform depth estimation based on a single query image devoid of depth information. The machine may calculate one or more visual descriptors from the single query image and obtain a corresponding depth descriptor for each visual descriptor from the generated mapping. Based on obtained depth descriptors, the machine creates depth information that corresponds to the submitted single query image.
Abstract translation: 在训练阶段,机器访问具有相应深度信息的参考图像。 该机器根据该信息计算视觉描述符和相应的深度描述符。 然后,机器生成将这些可视描述符与其相应的深度描述符相关联的映射。 在训练阶段之后,机器可以基于没有深度信息的单个查询图像来执行深度估计。 机器可以从单个查询图像计算一个或多个可视描述符,并从所生成的映射中获得每个可视描述符的相应深度描述符。 基于获得的深度描述符,机器创建与提交的单个查询图像相对应的深度信息。
-
公开(公告)号:US10255686B2
公开(公告)日:2019-04-09
申请号:US15408648
申请日:2017-01-18
Applicant: eBay Inc.
Inventor: Anurag Bhardwaj , Mohammad Haris Baig , Robinson Piramuthu , Vignesh Jagadeesh , Wei Di
Abstract: During a training phase, a machine accesses reference images with corresponding depth information. The machine calculates visual descriptors and corresponding depth descriptors from this information. The machine then generates a mapping that correlates these visual descriptors with their corresponding depth descriptors. After the training phase, the machine may perform depth estimation based on a single query image devoid of depth information. The machine may calculate one or more visual descriptors from the single query image and obtain a corresponding depth descriptor for each visual descriptor from the generated mapping. Based on obtained depth descriptors, the machine creates depth information that corresponds to the submitted single query image.
-
公开(公告)号:US20170193672A1
公开(公告)日:2017-07-06
申请号:US15408648
申请日:2017-01-18
Applicant: eBay Inc.
Inventor: Anurag Bhardwaj , Mohammad Haris Baig , Robinson Piramuthu , Vignesh Jagadeesh , Wei Di
CPC classification number: G06T7/50 , G06F17/3025 , G06F17/30256 , G06F17/30262 , G06F17/30277 , G06K9/00208 , G06K9/4609 , G06T7/194 , G06T7/62 , G06T2207/10024 , G06T2207/10028 , G06T2207/20081
Abstract: During a training phase, a machine accesses reference images with corresponding depth information. The machine calculates visual descriptors and corresponding depth descriptors from this information. The machine then generates a mapping that correlates these visual descriptors with their corresponding depth descriptors. After the training phase, the machine may perform depth estimation based on a single query image devoid of depth information. The machine may calculate one or more visual descriptors from the single query image and obtain a corresponding depth descriptor for each visual descriptor from the generated mapping. Based on obtained depth descriptors, the machine creates depth information that corresponds to the submitted single query image.
-
公开(公告)号:US09594774B2
公开(公告)日:2017-03-14
申请号:US14994459
申请日:2016-01-13
Applicant: eBay Inc.
Inventor: Anurag Bhardwaj , Mohammad Haris Baig , Robinson Piramuthu , Vignesh Jagadeesh , Wei Di
CPC classification number: G06T7/50 , G06F17/3025 , G06F17/30256 , G06F17/30262 , G06F17/30277 , G06K9/00208 , G06K9/4609 , G06T7/194 , G06T7/62 , G06T2207/10024 , G06T2207/10028 , G06T2207/20081
Abstract: During a training phase, a machine accesses reference images with corresponding depth information. The machine calculates visual descriptors and corresponding depth descriptors from this information. The machine then generates a mapping that correlates these visual descriptors with their corresponding depth descriptors. After the training phase, the machine may perform depth estimation based on a single query image devoid of depth information. The machine may calculate one or more visual descriptors from the single query image and obtain a corresponding depth descriptor for each visual descriptor from the generated mapping. Based on obtained depth descriptors, the machine creates depth information that corresponds to the submitted single query image.
Abstract translation: 在训练阶段,机器访问具有相应深度信息的参考图像。 该机器根据该信息计算视觉描述符和相应的深度描述符。 然后,机器生成将这些可视描述符与其相应的深度描述符相关联的映射。 在训练阶段之后,机器可以基于没有深度信息的单个查询图像来执行深度估计。 机器可以从单个查询图像计算一个或多个可视描述符,并从所生成的映射中获得每个可视描述符的相应深度描述符。 基于获得的深度描述符,机器创建与提交的单个查询图像相对应的深度信息。
-
-
-
-