为机器人操作中的高效视觉表征学习结构潜在点
Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
AI总结：
本文提出了一种新的预训练框架，通过学习混合表示-结构潜在点，结合隐式表示的表达能力和显式表示的结构先验，以提高机器人操作中的视觉表征效率和鲁棒性。
摘要：
当前基于3D感知的预训练方法在具身感知和操作中大多基于可微渲染框架，产生完全隐式神经场或完全显式几何基元。隐式表示虽然具有表达能力，但缺乏显式结构线索，而显式表示则保留几何信息但受到分辨率限制和泛化能力差的困扰。为了解决这些限制，我们提出了一种新的预训练框架，学习混合表示-结构潜在点。具体来说，我们将在点云自编码器的潜在空间中插入一个点-wise潜在变分自编码器，联合正则化点-wise特征和坐标向高斯先验。所得到的紧凑潜在保留了粗略的结构趋势，不编码精确几何，但捕捉了更丰富的粗糙形状和语义信息，有效结合了隐式表示的表达能力和显式表示的结构先验。此外，受先前工作的共享设计选择启发，我们开发了一种流线型、高效的3DGS基于渲染管道，故意保持轻量，提高效率的同时，让前端潜在模块有更大的表征能力。在RLBench、ManiSkill2和真实机器人平台上的大量评估显示，在任务成功率、样本效率和对视角和场景变化的鲁棒性方面均优于强基线。消融研究进一步确认了框架中每个组件对整体性能的重要性。
英文摘要：
Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either fully implicit neural fields or fully explicit geometric primitives. Implicit representations, while expressive, lack explicit structural cues, whereas explicit ones preserve geometry but suffer from resolution limits and weak generalization. To address these limitations, we propose a novel pretraining framework that learns a hybrid representation-structural latent points. Specifically, we insert a point-wise latent variational autoencoder into the latent space of a point-cloud autoencoder, jointly regularizing point-wise features and coordinates toward a Gaussian prior. The resulting compact latent preserves coarse structural tendencies, which do not encode precise geometry but capture richer rough shape and semantic information, effectively combining the expressiveness of implicit representations with the structural priors of explicit ones. In addition, informed by shared design choices in prior work, we develop a streamlined, efficient 3DGS-based rendering pipeline that is deliberately kept lightweight, improving efficiency while leaving greater representational capacity to the front-end latent module. Extensive evaluations on RLBench, ManiSkill2, and a real-robot platform demonstrate consistent gains in task success, sample efficiency, and robustness to viewpoint and scene variations over strong baselines. Ablation studies further confirm that each component of our framework is critical to overall performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
