A latent-space transformer framework poses 3D characters without skinning or fixed topologies, outperforming baselines and generalizing zero-shot to quadrupeds.
arXiv preprint arXiv:2506.21076 (2025) 4, 8
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Formalizes Fashion Detail Generation task, releases FDBench benchmark with 40K+ pairs, and proposes CFAD distillation method plus RL consistency reward that outperforms open-source baselines.
MeshReGen introduces a conditioned 3D geometry regenerator with VecSet that learns a regeneration prior via self-supervision and reports state-of-the-art results on controllable generation tasks.
citing papers explorer
-
Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters
A latent-space transformer framework poses 3D characters without skinning or fixed topologies, outperforming baselines and generalizing zero-shot to quadrupeds.
-
DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation
Formalizes Fashion Detail Generation task, releases FDBench benchmark with 40K+ pairs, and proposes CFAD distillation method plus RL consistency reward that outperforms open-source baselines.
-
MeshReGen: A Unified 3D Geometry Regeneration Framework
MeshReGen introduces a conditioned 3D geometry regenerator with VecSet that learns a regeneration prior via self-supervision and reports state-of-the-art results on controllable generation tasks.