WooLee - Revision history

imported>Projects221: /* PBRT */

2013-03-21T07:22:48Z

PBRT

← Older revision		Revision as of 07:22, 21 March 2013
Line 160:		Line 160:
	=== PBRT ===		=== PBRT ===
	<br>		<br>
	~~PBRt~~: www.pbrt.org		PBRT: www.pbrt.org
	<br>		<br>

	=== Computer Vision ===		=== Computer Vision ===
	Scharstein and Szeliski(2002). "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms". International Journal of Computer Vision 47: 7-42.		Scharstein and Szeliski(2002). "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms". International Journal of Computer Vision 47: 7-42.

imported>Projects221: /* From Blender to PBRT */

2013-03-21T07:22:02Z

From Blender to PBRT

← Older revision		Revision as of 07:22, 21 March 2013
Line 120:		Line 120:
	The figure below shows the conversion of 3D objects to a 3D scene. The figure on the right hand side below shows the PBRT-converted 3D scene from 3D objects in the figure on the left hand.		The figure below shows the conversion of 3D objects to a 3D scene. The figure on the right hand side below shows the PBRT-converted 3D scene from 3D objects in the figure on the left hand.
	<br>		<br>
	[[File:ObjectPbrt.png \|thumb\|500px\|center\| Figure 9 Object ~~Pbrt~~]]		[[File:ObjectPbrt.png \|thumb\|500px\|center\| Figure 9 Object PBRT]]
	<br>		<br>
	In PBRT exporter in Blender, we are able to set up the objects. We control the texture, material types, diffusion, etc. We configured as much as possible to mimic the 3D scene as close as the 3D initial objects.		In PBRT exporter in Blender, we are able to set up the objects. We control the texture, material types, diffusion, etc. We configured as much as possible to mimic the 3D scene as close as the 3D initial objects.

imported>Projects221: /* Data with Codes */

2013-03-21T07:21:40Z

Data with Codes

← Older revision		Revision as of 07:21, 21 March 2013
Line 173:		Line 173:
	==Data with Codes==		==Data with Codes==
	The following file contains all the data and codes that we have made and utilized.		The following file contains all the data and codes that we have made and utilized.
			<br>
	[[File:Scene3DMatlab.zip]]		[[File:Scene3DMatlab.zip]]

imported>Projects221: /* Appendix I - Code and Data */

2013-03-21T07:21:27Z

Appendix I - Code and Data

← Older revision		Revision as of 07:21, 21 March 2013
Line 171:		Line 171:
	= Appendix I - Code and Data =		= Appendix I - Code and Data =

	==~~Code~~==		==Data with Codes==
			The following file contains all the data and codes that we have made and utilized.
	[[File:Scene3DMatlab.zip]]		[[File:Scene3DMatlab.zip]]

	~~==Data==~~
	~~[[File:DataFile.zip \| zip file with my data]]~~

	= Appendix II - Work partition (if a group project) =		= Appendix II - Work partition (if a group project) =

imported>Projects221 at 07:19, 21 March 2013

2013-03-21T07:19:11Z

imported>Projects221: /* References - Resources and related work */

2013-03-21T07:16:38Z

References - Resources and related work

← Older revision		Revision as of 07:16, 21 March 2013
Line 154:		Line 154:
	= References - Resources and related work =		= References - Resources and related work =
	<br>		<br>
	== Blender ==		=== Blender ===
	<br>		<br>
	http://wiki.blender.org/index.php/		http://wiki.blender.org/index.php/
	http://wiki.blender.org/index.php/Doc:2.4/Manual/Introduction		http://wiki.blender.org/index.php/Doc:2.4/Manual/Introduction
	== PBRT ==		=== PBRT ===
	<br>		<br>
	PBRt: www.pbrt.org		PBRt: www.pbrt.org
	<br>		<br>
	== Computer Vision ==		=== Computer Vision ===
	Scharstein and Szeliski(2002). "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms". International Journal of Computer Vision 47: 7-42.		Scharstein and Szeliski(2002). "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms". International Journal of Computer Vision 47: 7-42.
	<br>		<br>

imported>Projects221: /* References - Resources and related work */

2013-03-21T07:16:12Z

References - Resources and related work

← Older revision		Revision as of 07:16, 21 March 2013
Line 153:		Line 153:

	= References - Resources and related work =		= References - Resources and related work =
			<br>
	~~References~~		== Blender ==
			<br>
	~~Software~~		http://wiki.blender.org/index.php/
			http://wiki.blender.org/index.php/Doc:2.4/Manual/Introduction
			== PBRT ==
			<br>
			PBRt: www.pbrt.org
			<br>
			== Computer Vision ==
			Scharstein and Szeliski(2002). "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms". International Journal of Computer Vision 47: 7-42.
			<br>
			Miao and Chen. "2nd Response to 'Feasibility of 3D reconstruction from a single 2D diffraction measurement" Retrieved from arxiv.org/pdf/0910.0272
			<br>
			Leens et al(2009). "Combining Color, Depth, and Motion for Video Segmentation." ICVS 2009.

	= Appendix I - Code and Data =		= Appendix I - Code and Data =

imported>Projects221 at 07:02, 21 March 2013

2013-03-21T07:02:48Z

imported>Projects221: /* Code */

2013-03-21T06:57:10Z

Code

← Older revision		Revision as of 06:57, 21 March 2013
Line 161:		Line 161:

	==Code==		==Code==
	[[File:~~CodeFile~~.zip]]		[[File:Scene3DMatlab.zip]]

	==Data==		==Data==

imported>Projects221: /* Appendix II - Work partition (if a group project) */

2013-03-21T06:48:32Z

Appendix II - Work partition (if a group project)

← Older revision		Revision as of 06:48, 21 March 2013
Line 167:		Line 167:

	= Appendix II - Work partition (if a group project) =		= Appendix II - Work partition (if a group project) =
	~~Brian and Bob gave~~ the ~~lectures~~. ~~Jon mucked around~~ on ~~the wiki~~.		We work closely together all the time almost everyday since we had started our project. For each part we all work together as well so it is difficult to partition. Roughly, for the preparation for the presentation,
			<br> Seul - worked on Blender, computer vision debugging
			<br> Seung Je - worked on PBRT rendering, computer vision algorithm coding
			<br> We also got lots of helpful advice from Andy Lai Lin.

← Older revision		Revision as of 07:19, 21 March 2013
Line 101:		Line 101:
	We decide to try simple 3D reconstruction. We will use 2 images: one is original image, the other is shifted image of the original one. By using two images mentioned above, we can get a depth that that could be used in 3D reconstruction. From the 2D images and for each certain portion we check how that portion is close to the portions in the other image.		We decide to try simple 3D reconstruction. We will use 2 images: one is original image, the other is shifted image of the original one. By using two images mentioned above, we can get a depth that that could be used in 3D reconstruction. From the 2D images and for each certain portion we check how that portion is close to the portions in the other image.
	==== Method 1: Autocorrelation ====		==== Method 1: Autocorrelation ====
	3D reconstruction can be done by using the concept of autocorrelation. The highest value of the autocorrelation is always the multiplication of itself, meaning the same image portion in our case. We fix the position of the portion in the original figure and move that in the second figure to compute the autocorrelation. For this computation we also include normalized constant to take weight into account. Once the highest value of the autocorrelation is found we select that that position of the second image corresponds to that of the first image.		3D reconstruction can be done by using the concept of autocorrelation. The highest value of the autocorrelation is always the multiplication of itself, meaning the same image portion in our case[Miao]. We fix the position of the portion in the original figure and move that in the second figure to compute the autocorrelation. For this computation we also include normalized constant to take weight into account. Once the highest value of the autocorrelation is found we select that that position of the second image corresponds to that of the first image.
	==== Method 2: Subtraction ====		==== Method 2: Subtraction ====
	Another approach is we subtract the image portion of original to that of the other. And then sum all the values computed. Other than this we do the same procedure: move the portion of the second image and compute the subtraction (also normalization is included here). In this case, however, the lowest values will let us know the position of the second image that corresponds to that of the first image.		Another approach is we subtract the image portion of original to that of the other. And then sum all the values computed [Leens]. Other than this we do the same procedure: move the portion of the second image and compute the subtraction (also normalization is included here). In this case, however, the lowest values will let us know the position of the second image that corresponds to that of the first image.
	==== Generate 3D depth Map ====		==== Generate 3D depth Map ====
	We can measure the distance of the positions. If an object is further from the camera views, the distance would be short. If an object is close to the camera views, the distance would be long. From this we can generate depth-map plot, giving high values to close objects and low values to distant objects.		We can measure the distance of the positions. If an object is further from the camera views, the distance would be short. If an object is close to the camera views, the distance would be long. From this we can generate depth-map plot, giving high values to close objects and low values to distant objects.
Line 133:		Line 133:
	We have coded 2 methods and tried to reconstruct the 3D depth using two files(codes attached in Data: slprac_ files). Following figure shows the result of the depth map plot.		We have coded 2 methods and tried to reconstruct the 3D depth using two files(codes attached in Data: slprac_ files). Following figure shows the result of the depth map plot.
	[[File:3DDepthResult.png \|thumb\|500px\|center\| Figure 11 3D Depth result]]		[[File:3DDepthResult.png \|thumb\|500px\|center\| Figure 11 3D Depth result]]
	From the figures we see that the depth map has not been generated well. Comparing to the 3D depth map ground truth, we realize that our result is not comparable to the reference value. This is because we do not have the initial depth math information about the scene. The backgrounds of two image do not change much at all. Thus, the result we have gotten represents the relative depth value. In order to get 3D depth map accurately, we need to have intial depth information to begin with ~~(레퍼렌스 넣기)~~.		From the figures we see that the depth map has not been generated well. Comparing to the 3D depth map ground truth, we realize that our result is not comparable to the reference value. This is because we do not have the initial depth math information about the scene. The backgrounds of two image do not change much at all. Thus, the result we have gotten represents the relative depth value. In order to get 3D depth map accurately, we need to have intial depth information to begin with [Scharstein].

	= Conclusions =		= Conclusions =
Line 143:		Line 143:

	== From 3D scenes to 3D objects ==		== From 3D scenes to 3D objects ==
	For 3D reconstruction, initially, the parallel shifted picture of original picture was gotten correctly. The algorithm that we decide to use lack in information as we assume that we do not have initial depth information about the 3D scenes. We could have improved the result, even without having the information about the depth, if we use larger portion, such as a square window for comparing the image matching computation~~. (레퍼렌스 달기)~~. Perhaps, we could assume that the depth is getting deeper from the bottom to the top of the image as it is what a camera normally look through.		For 3D reconstruction, initially, the parallel shifted picture of original picture was gotten correctly. The algorithm that we decide to use lack in information as we assume that we do not have initial depth information about the 3D scenes. We could have improved the result, even without having the information about the depth, if we use larger portion, such as a square window for comparing the image matching computation. Perhaps, we could assume that the depth is getting deeper from the bottom to the top of the image as it is what a camera normally look through.

	== Limitations ==		== Limitations ==

← Older revision		Revision as of 07:02, 21 March 2013
Line 19:		Line 19:

	<br>		<br>
	[[File:BlenderBasic.png \|thumb\|600px\|center\| Figure 2]]		[[File:BlenderBasic.png \|thumb\|600px\|center\| Figure 2 Blender window]]

	Take a cube as an example as shown fig.x. There is an object, which is a cube in this example, light source, and camera. On the left side of the figure.x, it shows whole scene that we created, on the right side, it shows the scene which is viewed through the camera.		Take a cube as an example as shown fig.x. There is an object, which is a cube in this example, light source, and camera. On the left side of the figure.x, it shows whole scene that we created, on the right side, it shows the scene which is viewed through the camera.
Line 40:		Line 40:
	To make texture on the object, texture image is needed, and it should be converted to .tga format. Then we put the texture image on the object. Also, we can apply the material to the object using texture menu shown in the figure.		To make texture on the object, texture image is needed, and it should be converted to .tga format. Then we put the texture image on the object. Also, we can apply the material to the object using texture menu shown in the figure.
	<br>		<br>
	[[File:BlenderTexture.png \|thumb\|500px\|center\| Figure ]]		[[File:BlenderTexture.png \|thumb\|500px\|center\| Figure 3 Control texture in Blender ]]
	=== control reflectance===		=== control reflectance===
	We are able to control reflectance, light source as well. In the case of reflectance, it is allowed to apply diffuse and specular reflectance on the object.		We are able to control reflectance, light source as well. In the case of reflectance, it is allowed to apply diffuse and specular reflectance on the object.
	<br>		<br>
	[[File:ReflectanceControl.png \|thumb\|400px\|center\| Figure ]]		[[File:ReflectanceControl.png \|thumb\|400px\|center\| Figure 4 Control reflectance in Blender ]]
	=== export to pbrt===		=== export to pbrt===
	Finally, the scene has been created by exporting the image to pbrt using exporter. Go to render menu, and click the export to pbrt.		Finally, the scene has been created by exporting the image to pbrt using exporter. Go to render menu, and click the export to pbrt.
	Here are some examples of 3D objects created via Blender.		Here are some examples of 3D objects created via Blender.
	<br>		<br>
	[[File:Monkey.png \|thumb\|300px\|center\| Figure ]]		[[File:Monkey.png \|thumb\|300px\|center\| Figure 5 Example image 1 ]]
	[[File:Sofa.png \|thumb\|300px\|center\| Figure ]]		[[File:Sofa.png \|thumb\|300px\|center\| Figure 6 Example image 2 ]]
	[[File:CupBlender.jpg \|thumb\|300px\|center\| Figure ]]		[[File:CupBlender.jpg \|thumb\|300px\|center\| Figure 7 Example image 3 ]]

	== Using PBRT to create 3D scene ==		== Using PBRT to create 3D scene ==
Line 110:		Line 110:
	In order to do 3D reconstruction. We need two images, and the viewpoints of them need to share at least one axis and perpendicular to the viewing direction. After exporting from Blender to PBRT, we can create another PBRT file viewing from another perspective by adjusting LookAt in default.pbrt. Utilizing the concept of linear algebra, we can deduce the points for the second camera. This way we would avoid uncertain error made in Blender because the computation of such point would be much more accurate than moving a camera. The following figure shows the vector of the camera.		In order to do 3D reconstruction. We need two images, and the viewpoints of them need to share at least one axis and perpendicular to the viewing direction. After exporting from Blender to PBRT, we can create another PBRT file viewing from another perspective by adjusting LookAt in default.pbrt. Utilizing the concept of linear algebra, we can deduce the points for the second camera. This way we would avoid uncertain error made in Blender because the computation of such point would be much more accurate than moving a camera. The following figure shows the vector of the camera.
	<br>		<br>
	[[File:ParallelCamera.png \|thumb\|200px\|center\| Figure]]		[[File:ParallelCamera.png \|thumb\|200px\|center\| Figure 8 Parallel camera]]
	<br>		<br>
	We know the two points consisting of the direction vector of the first camera. Using those points, we can get the vector points for the second camera.		We know the two points consisting of the direction vector of the first camera. Using those points, we can get the vector points for the second camera.
Line 120:		Line 120:
	The figure below shows the conversion of 3D objects to a 3D scene. The figure on the right hand side below shows the PBRT-converted 3D scene from 3D objects in the figure on the left hand.		The figure below shows the conversion of 3D objects to a 3D scene. The figure on the right hand side below shows the PBRT-converted 3D scene from 3D objects in the figure on the left hand.
	<br>		<br>
	[[File:ObjectPbrt.png \|thumb\|500px\|center\| Figure]]		[[File:ObjectPbrt.png \|thumb\|500px\|center\| Figure 9 Object Pbrt]]
	<br>		<br>
	In PBRT exporter in Blender, we are able to set up the objects. We control the texture, material types, diffusion, etc. We configured as much as possible to mimic the 3D scene as close as the 3D initial objects.		In PBRT exporter in Blender, we are able to set up the objects. We control the texture, material types, diffusion, etc. We configured as much as possible to mimic the 3D scene as close as the 3D initial objects.
Line 127:		Line 127:
	We generated 3D depth map ground truth plot, which is the theoretical values of the 3D depth(s_s2dRenderDepthMapExample.m). This can be useful to compter vision testing since it could be the reference values for 3D depth reconstruction. As an example, we attach the result of the 3D depth map ground truth for the 3 objects we created.		We generated 3D depth map ground truth plot, which is the theoretical values of the 3D depth(s_s2dRenderDepthMapExample.m). This can be useful to compter vision testing since it could be the reference values for 3D depth reconstruction. As an example, we attach the result of the 3D depth map ground truth for the 3 objects we created.
	<br>		<br>
	[[File:3DMGroundTruth.png \|thumb\|400px\|center\| Figure]]		[[File:3DMGroundTruth.png \|thumb\|400px\|center\| Figure 10 3D Ground truth]]
	<br>		<br>

	== 3D depth recontruction ==		== 3D depth recontruction ==
	We have coded 2 methods and tried to reconstruct the 3D depth using two files(codes attached in Data: slprac_ files). Following figure shows the result of the depth map plot.		We have coded 2 methods and tried to reconstruct the 3D depth using two files(codes attached in Data: slprac_ files). Following figure shows the result of the depth map plot.
	[[File:3DDepthResult.png \|thumb\|500px\|center\| Figure]]		[[File:3DDepthResult.png \|thumb\|500px\|center\| Figure 11 3D Depth result]]
	From the figures we see that the depth map has not been generated well. Comparing to the 3D depth map ground truth, we realize that our result is not comparable to the reference value. This is because we do not have the initial depth math information about the scene. The backgrounds of two image do not change much at all. Thus, the result we have gotten represents the relative depth value. In order to get 3D depth map accurately, we need to have intial depth information to begin with (레퍼렌스 넣기).		From the figures we see that the depth map has not been generated well. Comparing to the 3D depth map ground truth, we realize that our result is not comparable to the reference value. This is because we do not have the initial depth math information about the scene. The backgrounds of two image do not change much at all. Thus, the result we have gotten represents the relative depth value. In order to get 3D depth map accurately, we need to have intial depth information to begin with (레퍼렌스 넣기).