GS-VLA：基于高斯溅射的冻结VLA策略的即插即用视角规范化方法

中文摘要 AI 辅助

本文提出了一种轻量的即插即用框架，可提升视觉-语言-动作（Vision-Language-Action, VLA）策略对视角偏移的鲁棒性，无需对策略进行重新训练。据我们所知，这是首个直接利用基于3D高斯的新视角合成来实现VLA策略观测空间适配的方法。当前VLA的性能依赖于训练与部署阶段相机配置完全相同的隐含假设。我们的实验表明，即便是相机支架发生微小位移，在LIBERO基准测试中，最坏情况下的成功率也会从约90%降至约10%。现有方法如大规模微调或生成式数据增强，计算成本高昂且存在灾难性遗忘的风险。为解决该问题，视角偏移被重新表述为局部新视角合成问题。在局部性假设下，即相机扰动相对于工作空间保持在较小的有界区域内，视角规范化可简化为与场景和策略无关的去遮挡任务。本研究通过在冻结的VLA策略前添加一个参数规模为4M的3D高斯规范化器来实现该思路。在不修改策略权重的情况下，GS-VLA可在三个正交维度上提升性能：（1）策略架构；（2）未见任务套件；（3）扰动规模。这些结果表明，轻量视觉模块可在无需重新训练策略的情况下，恢复视角偏移导致的大部分性能损失。

英文摘要

This paper proposes a lightweight, plug-and-play framework that improves robustness to viewpoint shifts in Vision-Language-Action (VLA) policies without policy retraining. To our knowledge, this is the first approach to directly leverage 3D Gaussian-based novel-view synthesis for observation-space adaptation in VLA policies. Current VLA performance relies on the implicit assumption that training and deployment camera configurations are identical. Our experiments show that even a small displacement of the camera mount can reduce the success rate on the LIBERO benchmark from about 90% to about 10% in the worst case. Prior approaches, such as large-scale fine-tuning or generative data augmentation, are computationally expensive and risk catastrophic forgetting. To address this, viewpoint shifts are reformulated as a localized novel-view synthesis problem. Under a Locality assumption, that camera perturbations remain within a small bounded region relative to the workspace, viewpoint normalization reduces to a scene- and policy-independent disocclusion task. Our work implements this idea with a 4M-parameter 3D-Gaussian canonicalizer prepended to a frozen VLA policy. Without modifying policy weights, GS-VLA improves performance across three orthogonal axes: (1) Policy architectures, (2) Unseen task suites, and (3) Perturbation scales. These results show that a lightweight visual module can recover a large fraction of the performance lost under viewpoint shift, without policy retraining.

发表机构

• Dankook University（檀国大学）

机构由 AI 辅助整理，请以论文原文为准。