跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-17AI 評分35

HumanSkill-4D:無需訓練,以語言查詢可動態 Gaussian 化身的時空內容

HumanSkill-4D: Training-Free Language Querying of Animatable Gaussian Avatars in Space and Time

AI 導讀

HumanSkill-4D 是一個無需訓練的框架,透過共享多模態推理和幾何運算子,根據語言查詢選取可動態 Gaussian 化身的區域與動作區間。研究引入三個由人手標註的基準,評估結果顯示,HumanSkill-4D 在部件分割及 3D、4D 指代分割方面優於基線方法。每個化身只需數分鐘設定,並使用精簡記憶。

正文

Published on Oct 17

Authors:

,

,

Abstract

HumanSkill-4D enables language-driven selection of avatar regions and motion intervals via shared multimodal reasoning and geometric operators without training.

We introduce avatar referring segmentation, which selects regions of animatable Gaussian avatars from language queries. A query can also specify a pose or motion to select matching intervals. This lets users interact with avatars for local editing and motion inspection. However, making these selections with existing language Gaussian splatting methods poses two challenges: adjacent parts and garments are hard to separate and may be referred to indirectly (region ambiguity), while fine-grained motions can look alike in RGB (motion ambiguity). We address these challenges with HumanSkill-4D, a training-free framework that shares a multimodal large language model (MLLM) and geometric operators across avatars. For each avatar, a semantic memory links body-part and garment categories to persistent Gaussian regions and appearance descriptions. The MLLM uses category names and descriptions to select categories by appearance, relation, or function. To find matching intervals, it composes operators into programs that check query conditions on driving joint trajectories stored in a motion memory. These category choices and operator outputs make selections traceable, while composing or adding operators supports new motion conditions. To evaluate this task, we introduce three human-annotated benchmarks and show that HumanSkill-4D outperforms the baselines in part segmentation and 3D and 4D referring segmentation, with compact memories and only minutes of setup per avatar.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2610.24452

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.24452 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.24452 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.24452 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co