研究人员推出 HorizonStream，这是一种新颖的基于 Transformer 的架构，专为流式3D重建中的长视域注意力而设计。该方法通过将几何传播显式地分解为证据影响核，解决了现有方法在长序列中出现的漂移和抖动问题。HorizonStream 利用几何线性注意力进行多时间尺度证据传播，并结合具有时空 RoPE 的几何局部注意力进行可靠的3D匹配，从而能够在恒定内存和线性时间内稳定重建超过10,000帧的序列。 AI
影响 推动了流式3D重建能力的发展，可能改进机器人和增强现实等领域的应用。
排序理由 该集群包含一篇详细介绍3D重建新方法的学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
HorizonStream addresses long-term 3D reconstruction challenges by modeling geometric propagation through an evidence influence kernel, enabling stable, scalable streaming reconstruction with constant memory and linear time complexity.
arXiv:2605.23889v1 Announce Type: new Abstract: Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer from drift, jitter, or collapse on long sequences. We trace these failures…
Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer from drift, jitter, or collapse on long sequences. We trace these failures to a fundamental mismatch. Streaming geometry i…