---
id: 20260924-T0-13
title: "4DGS-JEPA：给动态高斯泼溅加上可复用的时序预测能力"
title_en: "4DGS-JEPA: Temporally Compositional Joint-Embedding Prediction for Dynamic Gaussian Splatting"
url: https://ai.daily.yangsir.net/daily/20260924-T0-13
issue_date: 2026-09-24
publish_date: 2026-09-23T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2609.25036
---

# 4DGS-JEPA：给动态高斯泼溅加上可复用的时序预测能力

研究者提出4DGS-JEPA，为动态高斯泼溅（Dynamic Gaussian Splatting）引入时序组合式联合嵌入预测。现有动态高斯泼溅方法主要针对重建、未来状态生成或渲染进行优化，而非学习可复用的预测性动态。4DGS-JEPA旨在让模型学到可迁移的动态预测表示，论文发布于arXiv。

## English Version

**4DGS-JEPA: Temporally Compositional Joint-Embedding Prediction for Dynamic Gaussian Splatting**

Researchers introduced 4DGS-JEPA, adding temporally compositional joint-embedding prediction to dynamic Gaussian splatting. Existing dynamic Gaussian splatting methods are optimized mainly for reconstruction, future-state generation, or rendering, rather than learning reusable predictive dynamics. 4DGS-JEPA aims to learn transferable predictive representations of dynamics. The paper is available on arXiv.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2609.25036)

**详情页**：https://ai.daily.yangsir.net/daily/20260924-T0-13

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*