English(EN) CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation

新的CRePE方法增强了视频生成模型中的相机控制

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了一种名为弯曲光线期望位置编码（CRePE）的新方法来改进视频生成模型。CRePE通过沿统一相机模型光线表示具有深度感知的图像标记分布来解决现有相机编码技术的局限性。这种方法增强了对相机参数、镜头类型和方向的控制，在针孔、广角和鱼眼镜头上表现良好。该方法可以与冻结的视频扩散Transformer无缝集成，还可以整合外部几何图以进行场景几何条件生成。 AI

影响增强了视频生成模型中的控制和保真度，可能改进需要精确相机和场景几何的应用。

排序理由详细介绍视频生成新技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍视频生成新技术的学术论文。[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, model release; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Seonghyun Jin, Youngmin Kim, Sunwoo Park, Jong Chul Ye · 2026-09-10 04:00

CRePE：用于统一相机控制视频生成的弯曲射线期望位置编码

arXiv:2605.12938v2 Announce Type: replace-cross Abstract: Video world models should predict future appearance in a way that remains consistent with 3D scene structure, camera motion, and lens geometry. Existing attention-level camera encodings, however, either describe each token…

本文如何被排名

报道来源 [1]

CRePE：用于统一相机控制视频生成的弯曲射线期望位置编码

相关实体

相关话题