# UniT：基于群自回归Transformer的统一几何学习

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-20 08:00
- AIHOT 分数：55
- AIHOT 链接：https://aihot.virxact.com/items/cmpeus3nt00v1sljwzsw8rqcs
- 原文链接：https://arxiv.org/abs/2605.21131

## AI 摘要

UniT是一个统一几何感知模型，旨在将在线感知、离线重建、多模态整合等分散能力整合到单一框架。其核心是群自回归Transformer，将传感器观测组作为基本单元，通过改变组大小，在同一过程中自然统一在线（多步单帧组）与离线（单步多帧组）模式。为处理长序列，模型采用队列式KV缓存机制，并利用无锚点关系建模来丢弃过时记忆。此外，模型引入尺度自适应几何损失以增强跨场景的尺度泛化能力。在多个任务的基准测试中，UniT实现了统一几何感知的最先进性能。

## 正文

Recent feed-forward models have significantly advanced geometry perception for inferring dense 3D structure from sensor observations. However, its essential capabilities remain fragmented across multiple incompatible paradigms, including online perception, offline reconstruction, multi-modal integration, long-horizon scalability, and metric-scale estimation. We present UniT, a unified model built upon a novel Group Autoregressive Transformer, which reformulates these seemingly disparate capabilities within a single framework. The key idea is to treat groups of sensor observations as the basic autoregressive units and predict the corresponding point maps in an anchor-free and scale-adaptive manner. More specifically, diverse view configurations in both online and offline settings are naturally unified within a single group autoregression process. By varying the group size, online mode operates over multiple autoregressive steps with single-frame groups, whereas offline mode aggregates a multi-frame group in a single forward pass. Meanwhile, a queue-style KV caching mechanism ensures bounded autoregressive memory over long horizons. This is enabled by reducing long-range dependencies on early frames through anchor-free relational modeling, thereby allowing outdated memory to be discarded on the fly. To improve metric-scale generalization across scenes, a scale-adaptive geometry loss is further introduced within this framework. It couples relative geometric constraints with a partial absolute scale term, implicitly regularizing global scale and inducing a progressive transition from scale-invariant geometry to metric-scale solutions. Together with a dedicated modal attention module for integrating auxiliary modalities, UniT achieves state-of-the-art performance in unified geometry perception, as validated on ten benchmarks spanning seven representative tasks.