1.1 360-degree Renders 5 pts

Create a 360-degree gif video that shows many continuous views of the provided cow mesh.

360-degree turntable render of the cow mesh
Figure 1. 360° turntable render of the cow mesh.

1.2 Re-creating the Dolly Zoom 10 pts

Recreate the dolly zoom effect in PyTorch3D.

Dolly zoom effect on the cow-on-plane mesh
Figure 2. Dolly zoom: FOV increases from 5° to 120° while the camera distance is adjusted (d = h / tan(fov/2)) to keep the cow's apparent size constant.

2.1 Constructing a Tetrahedron 5 pts

Construct a tetrahedron mesh and render it from multiple viewpoints. List how many vertices and faces your mesh has.

360-degree render of a tetrahedron mesh
Figure 3. 360° render of the tetrahedron mesh.

Vertices: 4 · Faces: 4

2.2 Constructing a Cube 5 pts

Construct a cube mesh and render it from multiple viewpoints. List how many vertices and faces your mesh has.

360-degree render of a cube mesh
Figure 4. 360° render of the cube mesh.

Vertices: 8 · Faces: 12 (6 quad faces × 2 triangles each)

3. Re-texturing a Mesh 10 pts

Retexture the cow mesh so that the color smoothly changes from the front of the cow (color1) to the back of the cow (color2), interpolated linearly by z-coordinate. Describe your choice of color1 and color2.

Cow mesh retextured with a front-to-back color gradient
Figure 5. Retextured cow, gradient from front to back.

color1 (front, z_min) = [1, 0, 0] (red) · color2 (back, z_max) = [0, 0, 1] (blue)

Red and blue look nice and also have pretty high contrast, so this gradient from head red to body blue is my choice.

4. Camera Transformations 10 pts

For each image below, find the relative camera transformation (R_relative, T_relative) that produced it, where the new camera extrinsics are R = R_relative @ R_0 and T = R_relative @ T_0 + T_relative. Describe in words what R_relative and T_relative are doing for each.

Transform 1

R_relative = [[0, 1, 0], [-1, 0, 0], [0, 0, 1]]
T_relative = [0, 0, 0]

R_relative is a 90° rotation about the camera's own viewing (z) axis. T_relative is zero, so the camera doesn't move at all.

Transform 2

R_relative = [[0, 0, 1], [0, 1, 0], [-1, 0, 0]]
T_relative = [-3, 0, 3]

R_relative is a 90° rotation about the vertical world y-axis. T_relative repositions the camera so that after the rotation it still sits at the correct distance and angle looking towards the cow.

Transform 3

R_relative = [[1, 0, 0], [0, 1, 0], [0, 0, 1]]
T_relative = [0, 0, 2]

R_relative is the identity, so the viewing angle is unchanged from the default. T_relative moves the camera straight back along its own viewing axis, increasing the distance (zooming out) from 3 to 5.

Transform 4

R_relative = [[1, 0, 0], [0, 1, 0], [0, 0, 1]]
T_relative = [0.5, -0.5, 0]

R_relative is again the identity, so the viewing angle doesn't change. T_relative shifts the camera sideways (no change in distance), which re-centers the frame off the cow's middle.

5.1 Rendering Point Clouds from RGB-D Images 10 pts

Construct 3 point clouds from the two provided RGB-D images of a plant: the point cloud from image 1, the point cloud from image 2, and the union of the two. Show a gif of each, side-by-side, from multiple viewpoints.

5.2 Parametric Functions 10 + 5 pts

Render a torus point cloud by sampling its parametric function, and make sure the hole is visible. Then render a 360° gif on any new object of your choice.

Torus 10 pts

360-degree render of a parametric torus point cloud
Figure 6. Torus point cloud, sampled from its parametric function — hole clearly visible throughout the rotation.

New object: Trefoil knot +5 pts

360-degree render of a trefoil knot point cloud
Figure 7. Trefoil knot, rendered as a point cloud by sweeping a tube (via a per-point local frame) around the classic trefoil parametric curve.

5.3 Implicit Surfaces 15 + 5 pts

Render a torus as a mesh defined by an implicit function, using marching cubes. Discuss the tradeoffs between rendering as a mesh vs. a point cloud. Then render a 360° gif on any new object of your choice (can differ from 5.2).

Torus 10 pts

360-degree render of an implicit-surface torus mesh
Figure 8. Torus mesh, extracted via marching cubes from the implicit function (sqrt(x²+y²) - R)² + z² - r² = 0.

Mesh vs. point cloud tradeoffs 5 pts

The tradeoff is mostly in speed and quality. Mesh rendering gives higher visual quality for the same resolution. because faces are interpolated across their surface, a torus with only ~50K vertices still renders as a smooth surface with no gaps. Point clouds, on the other hand, rely on splatting a fixed-size disk per point, so getting a gap-free surface either takes far more points or a bigger point radius, which then blurs fine detail and makes it look fuzzy rather than crispy (it's visually quite obvious when compare 5.1/5.2 gifs with the 5.3 mesh gifs). On the other hand, getting the point cloud is straightforward: sample the parametric function and the job is done. Getting the mesh required a more expensive step: evaluate the implicit function on a dense 3D voxel grid and run marching cubes to extract the surface, which is both slower and cost more memory than just sampling points directly. Point clouds are also easier to edit/combine (Q5.1), whereas merging or editing meshes needs to respect face connectivity (a lot of work). So overall: point clouds are cheap, flexible, and quick to generate, while meshes cost more to build but render higher quality.

New object: Trefoil knot +5 pts

360-degree render of an implicit-surface trefoil knot mesh
Figure 9. Trefoil knot mesh, extracted via marching cubes from an implicit distance field to the trefoil's parametric curve (dist_to_curve(x,y,z) - tube_r = 0).

(Extra Credit) 6. Do Something Fun +10 pts

Create your own 3D structures, or render something in an interesting way, or creatively texture something — the (3D) world is your oyster!

360-degree render of a rippling rainbow-textured cow mesh
Figure 10. Wobbly rainbow cow: each vertex's radial distance from the vertical axis is modulated by a traveling sine wave based on height and time (scale = 1 + A·sin(f·y + t)), giving a jelly-like ripple as the cow spins, textured with a rainbow gradient from its normalized (x, y, z) position.

(Extra Credit) 7. Sampling Points on Meshes +10 pts

Write a function that takes a triangle mesh and a number of samples, and outputs a point cloud via area-weighted stratified sampling. Using the cow mesh, sample 10, 100, 1000, and 10000 points. Render each point cloud and the original mesh side-by-side.

Cow mesh side-by-side with point clouds sampled at 10, 100, 1000, and 10000 points
Figure 11. Left to right: original cow mesh, then point clouds of 10, 100, 1,000, and 10,000 points sampled via area-weighted stratified sampling (face chosen ∝ area, then a uniform random barycentric coordinate on that face).