研究人员开发了两种新方法来提高视觉几何Transformer的效率。一种方法“Good Token Hunting”采用两阶段框架，通过选择关键Token来降低计算成本，在包含500张图像的场景中实现了超过85%的加速。另一种方法“GeoWeaver”则侧重于在场景推理之前，利用几何证据来锚定视觉Token，通过自适应地将几何抽象分配给单个Token来增强空间推理能力。 AI
影响 这些方法为视觉几何Transformer提供了显著的加速和改进的推理能力，有望加速3D重建和空间理解任务。
排序理由 两篇学术论文详细介绍了改进视觉Transformer架构的新颖方法。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2605.23892v1 Announce Type: cross Abstract: Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically …
Visual geometry transformers are accelerated through a two-stage token selection framework that reduces computational costs while maintaining performance.
Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the input sequence length due to the global a…
arXiv:2605.22558v1 Announce Type: new Abstract: Spatio-temporal reasoning in vision-language models requires visual representations that preserve physical geometry rather than merely semantic appearance. Recent multimodal models incorporate geometric information through structura…
Spatio-temporal reasoning in vision-language models requires visual representations that preserve physical geometry rather than merely semantic appearance. Recent multimodal models incorporate geometric information through structural branches, 3D-aware supervision, reasoning-stag…