PulseAugur
中
实时 08:26:14
English(EN) Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction

Scal3R方法通过多相对位姿查询增强在线3D重建

研究人员开发了Scal3R,一种改进长视频在线3D重建的新方法。通过使用轻量级token和冻结骨干网络将问题重新表述为多参考相对位姿查询,Scal3R显著减少了漂移。该系统在包括KITTI、Virtual KITTI、Sintel、TUM-Dynamic、ScanNet和7-Scenes在内的各种数据集上取得了最先进的性能,同时仅需要原始骨干网络约1%的参数,并在单个GPU上8小时内收敛。 AI

影响 提高了长视频在线3D重建的可扩展性和准确性,可能影响机器人和自主系统中的应用。

排序理由 发布了一篇详细介绍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 2 个来源。 我们如何撰写摘要 →

Scal3R方法通过多相对位姿查询增强在线3D重建

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
发布了一篇详细介绍3D重建新方法的学术论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
76 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Scal3R:学习高效多相对位姿查询以实现可扩展的在线3D重建

    Scal3R improves long-video online 3D reconstruction by querying multi-reference relative poses with lightweight tokens and pose-graph optimization, reducing drift without retraining the backbone.

  2. arXiv cs.CV TIER_1 English(EN) · Chin-Yang Lin, Yang-Che Sun, Cheng Sun, Fu-En Yang, Min-Hung Chen, Yen-Yu Lin, Wei-Chen Chiu, Yu-Lun Liu ·

    Scal3R:学习高效多相对位姿查询以实现可扩展的在线3D重建

    arXiv:2609.04201v1 Announce Type: new Abstract: Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed first-frame anchor forces extrapolation far beyond the training distribution. Small drifts accumulate and ampli…