16-825 Assignment 1: Rendering Basics with PyTorch3D

1. Practicing with Cameras

1.1 360-degree Renders

360 degree render of the cow mesh

1.2 Re-creating the Dolly Zoom

Dolly zoom effect on the cow mesh

2. Practicing with Meshes

2.1 Constructing a Tetrahedron

4 vertices, 4 triangle faces.

360 degree render of a tetrahedron mesh

2.2 Constructing a Cube

8 vertices, 12 triangle faces.

360 degree render of a cube mesh

3. Re-texturing a Mesh

Selected 2 distinct colors for contrast: blue (front) and orange (back).

Retextured cow mesh with a color gradient from front to back

4. Camera Transformations

Camera transform: 90 degree roll
Rrelative = 010 -100 001 Trelative = 000

R_relative rotates the camera 90 degrees about the viewing axis. T_relative does not move the camera.

Camera transform: move back
Rrelative = 100 010 001 Trelative = 002

R_relative does not rotate the camera. T_relative moves the camera 2 units further back along the z-axis.

Camera transform: shift up and right
Rrelative = 100 010 001 Trelative = 0.5-0.50

R_relative does not rotate the camera. T_relative shifts the camera sideways and up.

Camera transform: 90 degree yaw and reposition
Rrelative = 001 010 -100 Trelative = -303

R_relative rotates the camera 90 degrees about the vertical axis. T_relative repositions the camera to the side of the cow.

5. Rendering Generic 3D Representations

5.1 Rendering Point Clouds from RGB-D Images

Point cloud from first RGBD image
Point cloud from second RGBD image
Union of both point clouds

5.2 Parametric Functions

360 degree render of a torus point cloud

Custom shape: a helix, parameterized by a coil angle and a tube angle, with the tube swept around a rising, turning centerline.

360 degree render of a helix point cloud

5.3 Implicit Surfaces

360 degree render of a torus mesh from an implicit function

Meshes vs. point clouds:

360 degree render of a custom implicit surface mesh

(Extra Credit) 6. Do Something Fun

Wanted to simulate a cool transform: scattered noise that assembles itself into a mesh. The point cloud converges into shape, then hands off to the solid textured mesh. Generated for both the cow and cat meshes.

Point cloud noise assembling into a textured cow mesh
Point cloud noise assembling into a textured cat mesh

(Extra Credit) 7. Sampling Points on Meshes

Point cloud sampled from the cow mesh with 10 points
Point cloud sampled from the cow mesh with 100 points
Point cloud sampled from the cow mesh with 1000 points
Point cloud sampled from the cow mesh with 10000 points