Figure 3. Overview of CUPID’s pipeline. From a single input image, CUPID first generates an occupancy and a UV cube in canonical
space. Then, a Perspective-n-Point (PnP) solver (i.e., Eq. 2) recovers the camera pose. Using this recovered camera pose, we extract pose-
aligned conditioning latents and visual features (i.e., Eq. 3), along with noisy structured latents, to generate the geometry and appearance
features, which will be decoded to the 3D Gaussian splats and mesh.