Preprint
Oct 2026
Position Forcing: Self-Conditioning 3D Generation
Recent single-stage 3D generative models commonly adopt VecSet representations, encoding 3D shapes as unordered sets of latent tokens. However, compared with two-stage methods that provide explicit positional guidance, these models must implicitly infer token positions throughout denoising, limiting their generation qu...
Zi-Juan Ouyang, Ze-Qiang Lai, Jia-Rui Chen et al.
· 0 citations