System and method for three-dimensional scanning and for capturing a bidirectional reflectance distribution function
A method for generating a three-dimensional (3D) model of an object includes: capturing images of the object from a plurality of viewpoints, the images including color images; generating a 3D model of the object from the images, the 3D model including a plurality of planar patches; for each patch of the planar patches: mapping image regions of the images to the patch, each image region including at least one color vector; and computing, for each patch, at least one minimal color vector among the color vectors of the image regions mapped to the patch; generating a diffuse component of a bidirectional reflectance distribution function (BRDF) for each patch of planar patches of the 3D model in accordance with the at least one minimal color vector computed for each patch; and outputting the 3D model with the BRDF for each patch.
1. A computer system for training a convolutional neural network to classify patches of an object as clean or defective based upon a feature vector, the computer system comprising:
one or more processors; and
one or more computer-readable media having stored thereon executable instructions that when executed by the one or more processors configure the computer system to:
receive a plurality of training 3D models of objects and corresponding training classifications,
render a plurality of views of the 3D models with controlled lighting to generate training data,
compute a plurality of feature vectors from the views by the convolutional neural network, wherein the plurality of feature vectors are based upon a plurality of features rendered within the plurality of views,
compute parameters of the convolutional neural network,
compute a training error metric between the training classifications of the training 3D models with outputs of the convolutional neural network configured based on the parameters,
compute a validation error metric in accordance with a plurality of validation 3D models separate from the training 3D models, and
in response to determining that the training error metric and the validation error metric satisfy a threshold, configure the neural network in accordance with the parameters.
2. The computer system of claim 1 , wherein at least one of the plurality of features is computed based on color information of the object in the plurality of views of the object.
3. The computer system of claim 1 , wherein at least one of the plurality of features is computed based on shape information of the object in the plurality of views of the object.
4. The computer system of claim 1 , wherein at least one of the plurality of features is computed based on color information and shape information of the object in the plurality of views of the object.
5. The computer system of claim 1 , wherein the 3D models comprise point clouds.
6. The computer system of claim 1 , wherein the plurality of views are captured by a plurality of different cameras.
7. The computer system of claim 6 , wherein the plurality of views of the object are captured while the objects are on a conveyor belt.
8. The computer system of claim 1 , wherein the plurality of views of the objects from a plurality of viewpoints are captured by a single camera.
9. The computer system of claim 8 , wherein the camera is a stereoscopic depth camera comprising a first infrared camera, a second infrared camera, and a color camera.
10. The computer system of claim 1 , wherein the 3D model is a model of less than the entire exterior surface of the object.
11. A computer-implemented method executed on one or more processors for training a convolutional neural network to classify patches of an object as clean or defective based upon a feature vector, the method comprising:
receiving a plurality of training 3D models of objects and corresponding training classifications,
rendering a plurality of views of the 3D models with controlled lighting to generate training data,
computing a plurality of feature vectors from the views by the convolutional neural network, wherein the plurality of feature vectors are based upon a plurality of features rendered within the plurality of views,
computing parameters of the convolutional neural network,
computing a training error metric between the training classifications of the training 3D models with outputs of the convolutional neural network configured based on the parameters,
computing a validation error metric in accordance with a plurality of validation 3D models separate from the training 3D models, and
in response to determining that the training error metric and the validation error metric satisfy a threshold, configuring the neural network in accordance with the parameters.
12. The computer-implemented method of claim 11 , wherein at least one of the plurality of features is computed based on color information of the object in the plurality of views of the object.
13. The computer-implemented method of claim 11 , wherein at least one of the plurality of features is computed based on shape information of the object in the plurality of views of the object.
14. The computer-implemented method of claim 11 , wherein at least one of the plurality of features is computed based on color information and shape information of the object in the plurality of views of the object.
15. The computer-implemented method of claim 11 , wherein the 3D models comprise point clouds.
16. The computer-implemented method of claim 11 , wherein the plurality of views are captured by a plurality of different cameras.
17. The computer-implemented method of claim 16 , wherein the plurality of views of the object are captured while the objects are on a conveyor belt.
18. The computer-implemented method of claim 11 , wherein the plurality of views of the objects from a plurality of viewpoints are captured by a single camera.
19. The computer-implemented method of claim 18 , wherein the camera is a stereoscopic depth camera comprising a first infrared camera, a second infrared camera, and a color camera.
20. The computer-implemented method of claim 11 , wherein the 3D model is a model of less than the entire exterior surface of the object.