Voxel grid fitted using binary cross-entropy loss.
5,000 points initialized from N(0, 1) are fitted with symmetric squared Chamfer loss for 1,500 Adam steps.
Level-4 sphere fitted with Chamfer + 0.1 x Laplacian loss, shown at five stages over 1,500 Adam steps.
A fine-tuned ResNet18 and 512-1024-2048-32768 MLP predict a 32x32x32 voxel grid using weighted BCE + Dice loss (4,000 Adam steps, batch 32, validation-selected threshold 0.75), achieving 73.88% F1@0.05 on 678 test chairs.
ResNet18 with a 512-1024-2048-3000 MLP predicts 1,000 points using squared Chamfer loss (3,000 Adam steps, batch 32), achieving 80.13% F1@0.05 on 678 test chairs; Chamfer distance does not guarantee equal point spacing, so point clusters may occur.
ResNet18 with a 512-1024-2048-7686 MLP deforms ico_sphere(4) using Chamfer + 0.1 x Laplacian loss (3,000 Adam steps, batch 32, CPU); points achieve the best F1@0.05 by placing samples freely, while coarse voxels lose thin details and fixed-topology meshes can fold.
| Representation | F1@0.05 |
|---|---|
| 32x32x32 voxels | 73.88% |
| 1,000 points | 80.13% |
| 2,562-vertex mesh | 72.11% |
With matched Chamfer + 0.1 x uniform Laplacian training (3,000 Adam steps, batch 32, CPU), ico_sphere(2) cuts decoder parameters by 80.3% for a 1.92-point F1@0.05 drop, while the finer model's visible folds show that higher surface F1 does not guarantee cleaner mesh geometry.
| Template | Vertices | Faces | Decoder parameters | F1@0.05 |
|---|---|---|---|---|
| ico_sphere(2) | 162 | 320 | 3,620,326 | 70.20% |
| ico_sphere(4) | 2,562 | 5,120 | 18,373,126 | 72.11% |
Sliding 24x24 black masks (stride 12) over Task 2.2 inputs highlights seat and leg sensitivity in examples 2-3, while the largest shape change improves F1 in example 1, showing that sensitivity does not necessarily imply reduced accuracy.
| Example | Original F1 | Masked F1 | Change (points) |
|---|---|---|---|
| 1 | 79.30% | 81.15% | +1.85 |
| 2 | 92.53% | 79.23% | -13.30 |
| 3 | 91.39% | 82.24% | -9.15 |
A frozen Task 2.1 ResNet18 conditions a three-layer, 256-wide XYZ occupancy MLP trained with weighted BCE and selected by validation IoU, achieving 65.66% test F1@0.05 from a 32x32x32 grid at occupancy threshold 0.5.
Added after assignment update: I added this F1 evaluation after grading using the original checkpoint; I had not pulled the September 29 assignment update before submitting.
A frozen Task 2.2 ResNet18 conditions four UV-to-XYZ MLPs with three 128-wide ReLU hidden layers, trained for 6,000 Adam steps with symmetric squared Chamfer loss, achieving 71.41% test F1@0.05 on surfaces extracted using a 32x32 grid per patch.
Added after assignment update: I added this F1 evaluation after grading using the original checkpoint; I had not pulled the September 29 assignment update before submitting.
With identical frozen ImageNet ResNet18 encoders and 1,000-point decoders trained for 3,000 Adam steps on MPS, three-class training improves chair F1@0.05 by 1.26 points and produces clearer car and plane shapes, suggesting broader shape coverage without sacrificing chair accuracy, although thin chair details remain approximate.
| Training classes | Chair F1 (678) | Car F1 (368) | Plane F1 (405) |
|---|---|---|---|
| Chairs only | 73.78% | 63.46% | 58.22% |
| Chairs, cars, planes | 75.04% | 91.77% | 95.13% |