pith. machine review for the scientific record. sign in

We train the surface and skeleton Sparse Structure V AEs for24 hours on 4 NVIDIA A5000 24GB GPUs with a batch size of 4 per GPU

As mentioned in the main text, due to memory constraints we freeze Esurf, pre-extract the surface SLats for each item in the training split · arXiv 0770.0373

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.GR 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation

cs.GR · 2026-05-13 · unverdicted · novelty 8.0

Rigel3D jointly generates rigged 3D meshes with geometry, skeleton topology, joint positions, and skinning weights using coupled surface and skeleton latent representations for image-conditioned animation-ready asset synthesis.

citing papers explorer

Showing 1 of 1 citing paper.

  • Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation cs.GR · 2026-05-13 · unverdicted · none · ref 15

    Rigel3D jointly generates rigged 3D meshes with geometry, skeleton topology, joint positions, and skinning weights using coupled surface and skeleton latent representations for image-conditioned animation-ready asset synthesis.