16-825 Assignment 1: Rendering Basics with PyTorch3D

Results webpage — cameras, meshes, textures, point clouds, and implicit surfaces

1. Practicing with Cameras (15 points)

1.1 360-degree Renders (5 points)

I rendered the provided cow mesh from many viewpoints by sweeping the camera azimuth from 0° to 360° using look_at_view_transform, then saved the frames as a looping GIF.

360-degree cow render
Figure 1.1 — 360° turntable of the cow mesh

1.2 Dolly Zoom (10 points)

To keep the subject roughly the same size while changing FOV, camera distance satisfies distance ∝ 1 / tan(fov/2). As FOV increases the camera moves closer; as FOV decreases it moves farther, producing the classic dolly-zoom perspective warp on the ground plane.

Dolly zoom effect
Figure 1.2 — Dolly zoom on the cow-on-plane mesh

2. Practicing with Meshes (10 points)

2.1 Tetrahedron (5 points)

I manually defined a tetrahedron with a triangular base and an apex above it. The mesh has 4 vertices and 4 triangular faces.

Tetrahedron 360 render
Figure 2.1 — 360° tetrahedron (4 vertices, 4 faces)

2.2 Cube (5 points)

The cube has 8 vertices. Each of the 6 square sides is split into 2 triangles, giving 12 triangular faces.

Cube 360 render
Figure 2.2 — 360° cube (8 vertices, 12 faces)

3. Re-texturing a Mesh (10 points)

I recolored the cow with a front-to-back gradient based on each vertex’s z-coordinate:

Intermediate vertices use color = α·color2 + (1−α)·color1 with α = (z − z_min) / (z_max − z_min).

Retextured cow 360
Figure 3 — Retextured cow (front blue → back red)

4. Camera Transformations (10 points)

Starting from R0 = I and T0 = [0, 0, 3], new extrinsics are R = R_relative @ R0 and T = R_relative @ T0 + T_relative.

transform1 — rotate about Z

R_relative is a −90° rotation about the camera’s Z (optical) axis; T_relative = [0, 0, 0]. This rotates the image in-plane without changing camera distance.

transform1 expected
Expected
transform1 result
My result

transform3 — move farther

R_relative = I, T_relative = [0, 0, 2], so final T = [0, 0, 5]. The cow stays centered but appears smaller because the camera is farther away.

transform3 expected
Expected
transform3 result
My result

transform4 — translate in the image plane

R_relative = I, T_relative = [0.5, −0.5, 0]. No rotation; an XY shift moves the cow off-center in the frame.

transform4 expected
Expected
transform4 result
My result

transform2 — side view (rotate about Y)

R_relative is a 90° rotation about Y to view the cow from the side. After that rotation, R_relative @ T0 no longer places the subject at a good viewing distance, so T_relative = [−3, 0, 3] restores a reasonable camera translation.

transform2 expected
Expected
transform2 result
My result

5. Rendering Generic 3D Representations (45 points)

5.1 Point Clouds from RGB-D (10 points)

Using unproject_depth_image, I built point clouds from the two plant RGB-D views and their union. Below is a 360° GIF with the three clouds side-by-side (left → right: view 1, view 2, union). Single views are incomplete from some angles; the union is more complete.

Plant RGB-D point clouds
Figure 5.1 — Plant point clouds: view1 | view2 | union

5.2 Parametric Functions (10 + 5 points)

A torus was sampled from its parametric equations (R + r cos θ) cos φ, (R + r cos θ) sin φ, r sin θ with R = 1, r = 0.4 so the hole is visible.

Parametric torus
Figure 5.2a — Parametric torus point cloud

For the extra object (+5), I rendered a Möbius strip point cloud from its standard parametric equations.

Parametric Mobius strip
Figure 5.2b — Extra parametric object: Möbius strip

5.3 Implicit Surfaces (15 + 5 points)

The same torus is defined implicitly as the zero level-set of F(x,y,z) = (√(x²+y²) − R)² + z² − r², sampled on a voxel grid and converted to a mesh with marching cubes.

Implicit torus mesh
Figure 5.3a — Implicit torus mesh

Mesh vs point cloud tradeoffs (5 points)

For the extra implicit object (+5), I rendered a classic implicit heart surface.

Implicit heart mesh
Figure 5.3b — Extra implicit object: heart mesh

6. Extra Credit: Do Something Fun (+10 points)

I built a body-centered cubic (BCC) unit cell as a point cloud: 8 corner atoms, 1 center atom, and rods along the body diagonals from the center to each corner (similar to a chemistry lattice model). Each atom is a parametrically sampled sphere; each rod is a thin sampled cylinder.

BCC unit cell point cloud
Figure 6 — BCC unit-cell lattice (point cloud)

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

I implemented stratified surface sampling on the cow mesh: (1) pick a face with probability proportional to area, (2) sample a uniform barycentric coordinate, (3) form the 3D point on that triangle. Below: original mesh next to 10, 100, 1000, and 10000 samples.

Cow mesh surface samples
Figure 7 — Mesh | 10 | 100 | 1000 | 10000 sampled points