16-825 Assignment 2: Single View to 3D

1. Exploring Loss Functions

1.1. Fitting a voxel grid

1.2. Fitting a point cloud

1.3. Fitting a mesh

2. Reconstructing 3D from Single View

2.1. Image to voxel grid

2.2. Image to point cloud

2.3. Image to mesh

2.4: Quantitative Comparisons

2.5: Analyse effects of hyperparams variations

Varying Number of points in the point cloud: Increasing the number of points, gives a chance to the model to learn fine details Varying Chamfer loss weights:

2.6: Interpret your model

Visualizations like point cloud error heatmaps, activation maps, and 3D mesh comparisons provide valuable insights into a model's performance by highlighting areas of high error, revealing the model's focus during processing, and enabling direct comparison with ground truth. These methods complement numerical metrics and offer a clearer understanding of the model's spatial accuracy and precision at various thresholds.

3. Exploring Other Architectures/Datasets

3.3. Extended Dataset for Training

Here I did the full training for pointcloud. Training with more classes and datapoints results in better F1 scores