English(EN) OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning

OmniCam模型利用几何约束的姿态令牌学习生成相机轨迹

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-08 04:00

研究人员开发了OmniCam，这是一种新颖的自回归模型，旨在为视频生成、场景重建和机器人感知生成相机轨迹。该模型采用几何约束的姿态令牌学习方法，结合了全景点云编码器、混合绝对旋转和相对平移令牌化，以及带有3D目标锚点的独立几何和语义条件流。还构建了一个包含超过267,000条轨迹的新数据集OmniCaT来评估OmniCam，该模型在轨迹误差和碰撞率方面均显著优于现有方法。 AI

影响该模型可以提高AI生成视频的真实感和可控性，并增强机器人感知系统。

排序理由这是一篇详细介绍新模型和数据集的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍新模型和数据集的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Zhenyang Liu, Chenjie Cao, Yisu Zhang, Xuhui Zuo, Xiangyang Xue, Yanwei Fu, Tengfei Wang, Chunchao Guo · 2026-10-08 04:00

OmniCam：通过几何基础姿态令牌学习实现全向摄像头轨迹生成

arXiv:2610.09513v1 Announce Type: new Abstract: Camera trajectories control viewpoint changes in video generation, scene reconstruction, and robotic perception. Generating them from language requires both scene geometry and target-aware framing. We introduce OmniCam, an autoregre…

本文如何被排名

报道来源 [1]

OmniCam：通过几何基础姿态令牌学习实现全向摄像头轨迹生成

相关实体

相关话题