1. A bending imaging apparatus comprising:
a movable lens group which is movable along an optical axis thereof;
a motor which drives said movable lens group and includes a lead screw extending parallel to said optical axis;
a bending optical element arranged at at least one end of said optical axis to bend an object-emanating light bundle;
a housing which supports said movable lens group and said bending optical element;
a motor support bracket which includes a motor support portion that supports said motor, a screw support portion that supports an end of said lead screw, and a planar portion that is positioned between said motor support portion and said screw support portion and extends alongside said housing;
a cover member which includes a planar portion facing said planar portion of said motor support bracket; and
a fixer which fixes said cover member to said housing with a repulsive force generated to act between said planar portion of said motor support bracket and said planar portion of said cover member and with said motor support bracket pressed against said housing.
2. The bending imaging apparatus according to claim 1, wherein said fixer comprises an elastic member which is sandwiched and fixed between said planar portion of said motor support bracket and said planar portion of said cover member.
3. The bending imaging apparatus according to claim 1, further comprising a positioner which is positioned between said housing and said motor support bracket to position said housing and said motor support bracket with respect to each other.
4. The bending imaging apparatus according to claim 1, wherein said cover member is made of a resilient material, and
wherein said fixer comprises:
a plurality of engaging lugs formed on said cover member to protrude therefrom; and
a plurality of engaging portions formed on said housing to be engaged with said plurality of engaging lugs.
5. The bending imaging apparatus according to claim 4, wherein an engaging hole is formed in at least one of said engaging lugs, and
wherein at least one of said engaging portions of said housing comprises an engaging projection which is engaged in said engaging hole of said at least one of said engaging lugs.
6. The bending imaging apparatus according to claim 4, wherein at least one of said plurality of engaging lugs comprises an engaging protrusion, and
wherein at least one of said engaging portions includes an engaging recessed portion in which said engaging protrusion is engaged, said engaging recessed portion being formed on said housing.
7. The bending imaging apparatus according to claim 1, wherein said fixer comprises a plurality of engaging portions which are integrally formed with said housing to be engageable with said cover member.
8. The bending imaging apparatus according to claim 1, wherein said positioner is integrally formed with said housing.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. One or more processor-accessible tangible media comprising processor-executable instructions for image view synthesis, wherein the processor-executable instructions, when executed, direct a device to perform acts comprising:
registering an image to at least one reference model;
selecting a source block of one or more pixels of visual data from the image with regard to a destination block of the reference model based on a depth criterion and a color criterion;
wherein each pixel of each source block includes two or more depth levels, with each depth level having a separate color assignment;
wherein the color assignment of a frontmost layer of each pixel is the same color as a corresponding pixel of the image, and wherein a color assignment of each subsequent depth layer for each pixel is synthesized via multi-resolution texture synthesis;
applying each pixel of the source block of visual data from the image to the destination block of the reference model using a computed distance of the reference model to a position of a camera used to capture the image, and using the pixel color assignment from the depth layer closest to the computed distance to produce an image-augmented model;
wherein applying each pixel further comprises decreasing a proportional amount of the visual data of the source block from the image that is applied to the destination block of the reference model as a novel perspective viewpoint corresponding to a novel image view deviates further from a capture perspective viewpoint corresponding to the image; and
synthesizing the novel image view using the image-augmented model.
2. The one or more processor-accessible tangible media as recited in claim 1, wherein:
the act of selecting comprises selecting the source block of visual data from the image with regard to the destination block of the reference model responsive to a bias towards selecting proximate source blocks for proximate destination blocks to provide visual consistency for the proximate destination blocks.
3. A method for synthesizing a novel image view, the method comprising using a computing device to perform steps for:
registering an image to at least one reference model;
selecting a source block of visual data from the image with regard to a destination block of the reference model based on a source depth associated with the source block and a destination depth associated with the destination block;
wherein each pixel of each source block includes two or more depth levels, with each depth level having a separate color assignment;
wherein the color assignment of a frontmost layer of each pixel is the same color as a corresponding pixel of the image, and wherein a color assignment of each subsequent depth layer for each pixel is synthesized via multi-resolution texture synthesis;
applying each pixel of the source block of visual data from the image to the destination block of the reference model using a computed distance of the reference model to a position of a camera used to capture the image, and using the pixel color assignment from the depth layer closest to the computed distance to produce an image-augmented model;
wherein the step for applying comprises a step for decreasing a proportional amount of the source block of visual data from the image that is applied to the destination block of the reference model as a novel perspective viewpoint corresponding to a novel image view deviates further from a capture perspective viewpoint corresponding to the image; and
synthesizing the novel image view using the image-augmented model.
4. The method as recited in claim 3, wherein the step for selecting comprises:
selecting the source block of visual data from the image with regard to the destination block of the reference model based on a source color of the visual data of the source block and a destination color of a texture of the destination block.
5. The method as recited in claim 3, wherein the step for selecting comprises:
selecting the source block of visual data from the image with regard to the destination block of the reference model based on a source position of the source block and a destination position of the destination block.
6. The method as recited in claim 3, wherein the step for selecting comprises:
selecting the source block of visual data from the image with regard to the destination block of the reference model responsive to a bias towards selecting proximate source blocks for proximate destination blocks to provide visual consistency for the proximate destination blocks.
7. The method as recited in claim 3, wherein zero or more pixels corresponding to a destination position of the destination block of the reference model are not visible in the image because the destination position of the destination block is not within a captured view frustum through which the image was acquired or because the destination position of the destination block is occluded in the image by an object that is positioned between a capture position of the camera when the image was acquired and the destination position of the destination block.
8. The method as recited in claim 3, wherein the source block and the destination block correspond to a pixel.
9. The method as recited in claim 3, wherein the image is acquired with a captured view frustum; the method further comprising:
receiving input from a user to change a perspective of the captured view frustum to
a modified view frustum; and
wherein the step for synthesizing comprises using the image-augmented model with the modified view frustum to synthesize the novel image view.
10. The method as recited in claim 3, wherein the step for synthesizing comprises:
using augmented portions of the image-augmented model to extend the image to synthesize the novel image view, the novel image view having extended portions that are not included in the image.
11. A system for synthesizing a novel image view, comprising:
an image registration device that causes a computer to register an image to at least one reference model;
a source block selector device that causes a computer to select a source block of one or more pixels of visual data from the image with regard to a destination block of the reference model based on a source depth associated with the source block and a destination depth associated with the destination block;
wherein each pixel of each source block includes two or more depth levels, with each depth level having a separate color assignment;
wherein the color assignment of a frontmost layer of each pixel is the same color as a corresponding pixel of the image, and wherein a color assignment of each subsequent depth layer for each pixel is synthesized via multi-resolution texture synthesis;
a visual image data application device that causes a computer to apply the source block of visual data from the image to the destination block of the reference model using a computed distance of the reference model to a camera position at which the image was originally captured, and using the pixel color assignment from the depth layer closest to the computed distance to produce an image-augmented model;
wherein applying the source block of visual data further comprises decreasing a proportional amount of the visual data that is applied to the destination block as a novel perspective viewpoint corresponding to a novel image view deviates further from a capture perspective viewpoint corresponding to the image; and
an image view synthesizer device that causes a computer to synthesize the novel image view using the image-augmented model.
12. The system of claim 11, wherein the image view synthesizer causes the computer to synthesize the novel image view over a layered depth image that is at least approximately centered at the camera position at which the image was originally captured; and
wherein the layered depth image includes for each respective block a respective depth and normal of a scene point intersected by a corresponding original viewpoint.
13. The system of claim 12, wherein for a given block having a given depth, when a would-be neighboring block has multiple depth layers, a particular block on a layer with a particular depth that is closest to the given depth of the given block is assigned as the neighboring block.
14. The system of claim 12, wherein the visual image data application unit uses a shader to project the layered depth image onto the reference model by computing a distance between the reference model and the camera position and using a color of a block from a depth layer that is closest to the computed distance.
15. The system of claim 11, wherein the source block selector causes the computer to compute respective guiding values that reflect respective chrominance values and distances between the camera position and respective corresponding scene points.
16. The system of claim 11, wherein the source block selector causes the computer to search, for each given destination block of the reference model, for a neighborhood of source blocks that matches a neighborhood around each given destination block.
17. The system of claim 11, wherein the image view synthesizer causes the computer to blend texture from the reference model into the novel image view as a current viewpoint deviates from an original viewpoint.
18. The system of claim 17, wherein the image view synthesizer causes the computer to blend the texture from the reference model into the novel image view based on a blending factor that is set responsive to an angle between a normal and an original view direction and responsive to an angle between the original view direction and a new view direction.