Tag
Pumpire 提出了一个统一的基准测试，用于评估图像和视频级 3D 基础模型的点对点物理距离估计能力，并构建了包含 100 个真实场景、6400 帧的大型数据集 pumpire-6k，对 29 种基线配置进行了全面对比实验。
UniT is a unified feed-forward model for geometry perception using a Group Autoregressive Transformer that integrates multiple paradigms (online/offline, multi-modal, long-horizon) while maintaining metric-scale accuracy via scale-adaptive loss and queue-style KV caching. It achieves state-of-the-art performance on ten benchmarks spanning seven tasks.