提出DeGO框架，分离刚性与非刚性运动，提升动态场景占位预测精度。
Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation
- 将高斯体分解为刚性移动与非刚性变形两部分，分别更新
- 在Occ3D-NuScenes上对人相关物体提升13.5%，总体提升10.9%
- 适合自动驾驶中人体等柔性目标的动态建模
理解动态三维环境对安全自动驾驶至关重要，尤其涉及以人为中心的非刚性对象。现有弱监督占位预测方法多假设刚体运动，依赖帧间简单偏移，难以捕捉细微形变且缺乏时序一致性。为此，我们提出DeGO，一种结合解耦高斯形变与分层4D基础模型蒸馏的可变形高斯占位框架。DeGO分离刚性与非刚性运动，使每个高斯原语通过形变与偏移双重方式演化。同时，采用分层4D蒸馏策略，从VGGT基础模型迁移跨摄像头与跨帧知识，生成与基础模型对齐的特征，增强时序一致性。在Occ3D-NuScenes基准上的实验表明，该方法在弱监督下达到当前最优性能，人相关实例提升13.5%，整体提升10.9%。结果验证了形变感知与基础引导占位建模在动态场景理解中的有效性。代码已公开：https://github.com/vita-epfl/DeGO
原文摘要 · Abstract (English)
Understanding dynamic 3D environments is essential for safe autonomous driving, particularly when reasoning about human-centric, nonrigid agents. However, existing weakly supervised occupancy prediction frameworks predominantly assume rigid-body motion and rely on simple frame-to-frame offsets, limiting their ability to capture fine-grained deformations and maintain temporal coherence. To address this issue, we propose DeGO, a deformable Gaussian occupancy framework that unifies decoupled Gaussian deformation with factorized 4D foundation-model distillation. DeGO disentangles rigid and nonrigid motion, enabling each Gaussian primitive to evolve through both deformation and offset-based updates. In parallel, a factorized 4D distillation strategy transfers cross-camera and cross-frame knowledge from the VGGT foundation model, producing foundation-aligned features that enhance temporal consistency. Experiments on the Occ3D-NuScenes benchmark demonstrate that our method achieves state-of-the-art performance under weak supervision, delivering 13.5% gains on human-centric instances and 10.9% overall improvements. These results highlight the effectiveness of deformation-aware and foundation-guided occupancy modeling for dynamic scene understanding. The code is publicly available: https://github.com/vita-epfl/DeGO
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。