可变形高斯占用：以因子化蒸馏解耦刚性与非刚性运动
Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation
将高斯原语的刚性与非刚性形变解耦，并用 VGGT 4D 基础模型做因子化跨相机/跨帧蒸馏，为自动驾驶占用预测中的人体等非刚性目标提供可复用的形变建模与蒸馏监督思路。
原文依据 DeGO disentangles rigid and nonrigid motion, enabling each Gaussian primitive to evolve through both deformation and offset-based updates.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论理解动态三维环境对安全自动驾驶至关重要，尤其是在对以人为中心的非刚性智能体进行推理时。然而，现有的弱监督占用预测框架大多假设刚体运动并依赖简单的帧间偏移，限制了其捕捉细粒度形变与保持时序连贯性的能力。为解决该问题，我们提出 DeGO，一种可变形高斯占用框架，将解耦的高斯形变与因子化的 4D 基础模型蒸馏统一起来。DeGO 分离刚性与非刚性运动，使每个高斯原语能够通过形变与基于偏移的更新共同演化。同时，一种因子化 4D 蒸馏策略从 VGGT 基础模型迁移跨相机与跨帧知识，产生与基础模型对齐的特征以增强时序一致性。在 Occ3D-NuScenes 基准上的实验表明，本方法在弱监督下达到最优性能，在以人为中心的实例上取得 13.5% 的提升，整体提升 10.9%。这些结果凸显了形变感知与基础模型引导的占用建模对动态场景理解的有效性。
英文原文摘要 1261 字符
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.