日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

3D生成arXiv:2605.13129

Rigel3D: アニメーション対応3Dアセット生成のためのリグ認識潜在表現

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

シェア:XThreadsFacebookLINEはてブBluesky

リグ付きメッシュとしてアニメーション可能な3Dアセットを生成する手法を提案。形状とリグ構造を同時にモデル化し、骨格とスキニング重みを生成する。

詳しい要約

1. どんなもの?

- 3D generative model for animation-ready assets - outputs rigged meshes with skeletal rigs, joint hierarchies, skinning weights - enables use in games, film, simulation, virtual agents, embodied AI - method: Rigel3D - jointly models geometry and rig structure - uses coupled surface and skeleton structured latent representations - includes rig-aware autoencoder and two-stage latent generative model - open-vocabulary joint labeling module for retargeting

2. 先行研究と比べてどこがすごい?

- prior 3D generative models synthesize static assets - lack skeletal rigs, joint hierarchies, skinning weights - post-hoc auto-rigging methods attach rigs to completed shapes - Rigel3D jointly models geometry and rig structure - through coupled surface and skeleton structured latent representations - outperforms existing rigging baselines across multiple metrics - generates diverse, high-quality animation-ready assets

3. 技術・手法の肝は?

- rig-aware autoencoder - decodes coupled surface and skeleton structured latent representations - into mesh geometry, skeleton topology, joint coordinates, skinning weights - two-stage latent generative model - synthesizes both surface and skeleton representations - for image-conditioned generation - open-vocabulary joint labeling module - embeds generated joints into shared vision-language space - enables correspondence to arbitrary retargeting templates

4. どうやって有効だと検証した?

- experiments on large-scale rigged asset datasets - demonstrate method generates diverse, high-quality animation-ready assets - outperforms existing rigging baselines across multiple metrics - specific metrics and baselines not detailed in abstract

5. 議論はある?

- limitations or broader impacts not discussed in abstract - potential challenges in generalization to unseen categories not addressed - from abstract, no explicit discussion section

6. 次に読むべき論文は?

- post-hoc auto-rigging methods (e.g., RigNet, Auto-Rigging) - 3D generative models (e.g., GET3D, EG3D, MeshDiffusion) - vision-language models for joint labeling (e.g., CLIP) - animation and retargeting techniques

※ AIが要旨から生成した要約です。正確性は原文をご確認ください。

著者: Nikitas Chatzis, Marios Loizou, Evangelos Kalogerakis

分類: cs.GR, cs.CV

原文アブストラクト

Recent 3D generative models can synthesize high-quality assets, but their outputs are typically static: they lack the skeletal rigs, joint hierarchies, and skinning weights required for animation. This limits their use in games, film, simulation, virtual agents, and embodied AI, where assets must not only look plausible but also move plausibly. We introduce Rigel3D, a generative method for animation-ready 3D assets represented as rigged meshes. Unlike post-hoc auto-rigging methods that attach rigs to completed shapes, our method jointly models geometry and rig structure through coupled surface and skeleton structured latent representations. A rig-aware autoencoder decodes these representations into mesh geometry, skeleton topology, joint coordinates, and skinning weights, while a two-stage latent generative model synthesizes both surface and skeleton representations for image-conditioned generation. To support downstream animation workflows, we further introduce an open-vocabulary joint labeling module that embeds generated joints into a shared vision-language space, enabling correspondence to arbitrary retargeting templates. Experiments on large-scale rigged asset datasets demonstrate that our method generates diverse, high-quality animation-ready assets and outperforms existing rigging baselines across multiple metrics.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  3. 3パナソニックHDなど、触覚に即応する両手作業AI「T-Rex」を共同開発研究・技術
  4. 4SoftBank主導、Agile Robotsが5億ドル調達 NVIDIAと日立も参加資金調達
  5. 5NTT、ロボットの行動前に荷崩れを予測研究・技術

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI