TencentARC/DSR_Suite-Data

DSR Suite是一个旨在弥合视觉语言模型（VLMs）在动态空间推理（DSR）方面差距的综合资源。它解决了在3D空间中随时间（4D理解）推理对象几何和关系演变的挑战。该套件包括两个主要数据组件，这些组件是通过自动化流程从野外视频中构建的：

- **DSR-Train**：一个大规模训练数据集，包含50,000个自动生成的多选题答案对（QAs）。
- **DSR-Bench**：一个高质量基准数据集，包含1,484个经过人工标注的QAs，用于评估对象和场景级别的3D理解、视角变换和多对象交互。

数据生成流程利用了视觉基础模型来提取几何线索，如相机姿态、局部点云、对象掩码、方向和3D轨迹，以创建细粒度的程序化答案。

DSR Suite is a comprehensive resource designed to bridge the gap in dynamic spatial reasoning (DSR) for vision-language models (VLMs). It addresses the challenge of reasoning about the evolution of object geometry and relationships in 3D space over time (4D understanding). The suite includes two primary data components constructed from in-the-wild videos using an automated pipeline:

- **DSR-Train**: A large-scale training dataset featuring 50,000 automated multiple-choice question-answer pairs (QAs).
- **DSR-Bench**: A high-quality benchmark consisting of 1,484 QAs further refined by human annotators to evaluate object- and scene-level 3D understanding, viewpoint transformations, and multi-object interactions.

The data generation pipeline leverages vision foundation models to extract geometric cues such as camera poses, local point clouds, object masks, orientations, and 3D trajectories to create fine-grained, procedural answers.