Skip to main content
Search

Yeonjae Kim

1 related articles

Subscribe to updates
  1. arXiv

    Separately prepared parts snap into one object: VA-Assembly estimates translation, rotation and scale with same-view diffusion scores, no training

    VA-Assembly treats a single-image 3D reconstruction as the reference and directly optimizes the translation, rotation and scale of independently prepared part geometries, without part annotations, category priors or bounding-box initialization. It conditions a frozen view-conditioned diffusion model on reference renderings taken from the same camera view as the current part composition, so the score gradients align geometrically with that composition. Under translation-rotation, translation-scale and full-transformation protocols, its part-level transformation errors are lower than the corresponding registration and layout baselines, and ablations show same-view conditioning, not diffusion guidance alone, is the key.

You’re all caught up