Supplementary Materials for S-PIFu: Integrating Parametric Human Models with PIFu for Single-view Clothed Human Reconstruction
–Neural Information Processing Systems
In Figure 1, we show S-PIFu's results when given images of test subjects who wear large clothings (e.g. SMPL-X body, and yet S-PIFu is able reconstruct the human subjects accurately. Pixels that belong to human subject but not to the SMPL-X body act as a natural regularizer that prevents S-PIFu from being overly reliant on estimated SMPL-X meshes to reconstruct clothed human meshes. This happens because these pixels only have valid values for the RGB channels and not the channels of our 2D feature maps (i.e. C, B, and N. Recall that C refers to coordinate In Figure 1, we observe what would happen if we feed a noisy SMPL-X mesh (i.e. a SMPL-X mesh SMPL-X mesh's arms (both arms).
Neural Information Processing Systems
Aug-15-2025, 17:09:51 GMT
- Technology: