














F1@0.05$37.5$









F1@0.05$66.65$









F1@0.05$65.35$
| Voxel grid | Point cloud | Mesh | |
|---|---|---|---|
| F1@0.05 | $37.5$ | $66.65$ | $65.35$ |
| Training iterations | $400$ | $100$ | $1000$ |
I varied $n\in\{500, 1000, 5000\}$ (where $n$ is the number of points for the pointcloud model). I used the pretrained ResNet18 features, $100$ iterations, batch size $32$, learning rate $4\times10^{-4}$.
n_points | $500$ | $1000$ | $5000$ |
|---|---|---|---|
| F1@0.05 | $58.11$ | $66.65$ | $76.78$ |







AnalysisF1@0.05 rises steadily with the number of predicted points ($58.11 \to 66.65 \to 76.78$), because a denser prediction covers more of the chair's surface, especially thin legs and slats.
I colored the reconstructions by the nearest-neighbor distances (as in, nearest neighhbor to the ground truth mesh). Then each ground-truth point is colored by its distance to the nearest predicted point, so red points are parts of the chair the model missed.












ApproachFollowing Deep Geometric Prior for Surface Reconstruction, the ground-truth point cloud is covered with overlapping local patches (Poisson-disk anchors, then ball queries until every point is covered). Each patch is normalized (centered, scaled, and rotated into its principal axes) and gets its own MLP $\phi_i: \mathbb{R}^2 \to \mathbb{R}^3$ mapping 2D samples to 3D points. Patches are first fit locally by matching $\phi_i(u, v)$ to the patch points with a Sinkhorn algorithm and MSE loss, then refined with a consistency pass that keeps those correspondences fixed. Finally the patches are upsampled to produce the reconstructed point cloud shown above.