Assignment 1: Rendering Basics with PyTorch3D

16-825 Learning for 3D Vision | Fall 2026 | Jinyao Zhou (jinyaozh)

1.1 360-degree Renders (5 points)

360-degree turntable of the cow mesh

1.2 Re-creating the Dolly Zoom (10 points)

Dolly zoom on the cow

2.1 Constructing a Tetrahedron (5 points)

360-degree turntable of a tetrahedron

The mesh has 4 vertices and 4 triangle faces.

2.2 Constructing a Cube (5 points)

360-degree turntable of a cube

The mesh has 8 vertices and 12 triangle faces (2 triangles per cube side).

3. Re-texturing a mesh (10 points)

color1 = [1, 0, 0] (red)

color2 = [0, 0, 1] (blue)

Cow with a red-to-blue vertex gradient

4. Camera Transformations (10 points)

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

T_relative = [0, 0, 0]

Cow rolled 90 degrees in the image plane

R_relative = I

T_relative = [0, 0, 2]

Cow seen from further away

R_relative = I

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

Cow translated within the image plane

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

T_relative = [-3, 0, 3]

Cow seen from the side

5.1 Rendering Point Clouds from RGB-D Images (10 points)

Left to right: the point cloud from the first image, from the second image, and the union of the two.

Point clouds from image 1, image 2, and their union

5.2 Parametric Functions (10 + 5 points)

Torus

Parametric torus point cloud

Heart

Parametric heart surface point cloud

5.3 Implicit Surfaces (15 + 5 points)

Torus

Implicit torus mesh

Mesh vs. point cloud.

Heart

Implicit heart surface mesh

(Extra Credit) 7. Sampling Points on Meshes (10 points)

Left to right: the original cow mesh, then point clouds of 10, 100, 1000 and 10000 sampled points.

Cow mesh next to point clouds of 10, 100, 1000 and 10000 samples