PulseAugur
中
实时 09:46:14
English(EN) DesignAgent3D: Interactive 3D Scene Editing via Designer-like Multimodal Reasoning

AI代理通过新框架推进3D编辑和场景合成 · 已追踪10个来源

研究人员正在开发用于3D内容创建和编辑的高级AI代理,超越简单的生成,实现更复杂的操纵和控制。FlowEdit为运动生成和编辑提供了一个统一的框架,而Procedura则根据文本提示创建可编辑的、部分结构的程序化组件。DesignAgent3D和ViSculpt分别专注于交互式3D场景和几何编辑,利用代理推理来阐明用户意图并执行精确修改。MMLVE-Agent和LangDriveCTRL分别通过利用LLM和VLM来管理复杂指令并保持时空完整性,来处理一致的多镜头视频编辑和可控驾驶场景编辑。 AI

影响 这些进展标志着AI驱动的3D内容创建正朝着更直观、更可控的方向发展,有可能加速游戏开发、动画和虚拟现实领域的工作流程。

排序理由 多篇研究论文介绍了用于3D内容生成和编辑的新AI模型和框架。

在 arXiv cs.MA (Multiagent) 阅读 →

AI 生成摘要 · Google Gemini · 来自 12 个来源。 我们如何撰写摘要 →

AI代理通过新框架推进3D编辑和场景合成 · 已追踪10个来源

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
多篇研究论文介绍了用于3D内容生成和编辑的新AI模型和框架。
Source corroboration
12 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
product, 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
96 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 [12]

  1. arXiv cs.AI TIER_1 English(EN) · Junlin Li, Xinhao Song, Siqi Wang, Haibin Huang, Yili Zhao ·

    用于运动生成、编辑和结构内重定向的统一条件流

    arXiv:2604.13427v2 Announce Type: replace-cross Abstract: Text-driven motion editing and intra-structural retargeting, where skeletons share topology but may differ in bone lengths and rest pose, are traditionally handled by fragmented pipelines with incompatible inputs and repre…

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

    思考在镜头上:具有代理推理的一致性多镜头视频编辑

    An agentic framework combining LLMs and VLMs enables consistent, multi-instruction editing of long multi-shot videos while preserving spatiotemporal structure.

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

    程序化:具有程序化控制的 Agentic 3D 建模

    Procedura is a 3D modeling agent that generates editable, part-structured procedural assemblies with sharp geometry and validated articulation from text prompts.

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

    SemanticSlider3D:无需训练的3D物体连续语义编辑

    Fine-grained control over continuous semantic attributes of 3D objects is essential for 3D content creation, but is not well supported by conventional 3D modeling workflows or prompt-based interaction with existing generative AI tools. While slider-based methods have proven effec…

  5. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Xiangliang Zhang ·

    DesignAgent3D:通过类似设计师的多模态推理进行交互式3D场景编辑

    Text guided 3D scene editing provides an intuitive interface for modifying reconstructed environments, but remains difficult because natural language design requests are often semantically underspecified and must be grounded in cluttered 3D scenes. Existing methods typically form…

  6. arXiv cs.CV TIER_1 English(EN) · Chenyang Wu, Fuchen Long, Binyuan Huang, Xinlong Sun, Xi Chen, Chun-Le Guo, Chongyi Li ·

    思考在镜头上:具有代理推理的一致性多镜头视频编辑

    arXiv:2608.26809v1 Announce Type: new Abstract: While generative AI has significantly advanced video editing, existing methods primarily focus on single-shot or short video clips. Editing long videos with multiple instructions remains a formidable challenge. Naive chunking strate…

  7. arXiv cs.CV TIER_1 English(EN) · Youtian Lin, Yikang Yang, Zhanpeng Hu, Mengqi Zhou, Feihu Zhang, Xun Cao, Jiaheng Liu, Yao Yao ·

    程序化:具有程序化控制的 Agentic 3D 建模

    arXiv:2608.26238v1 Announce Type: new Abstract: Native 3D generators now recover impressive mesh geometry from a single image. However, a dense mesh stays soft where a machined object should be sharp, it carries no part decomposition, and it exposes no parameter a user could edit…

  8. arXiv cs.CV TIER_1 English(EN) · Bo Pang, Jiaqi Pan, Xiaocheng Zhang, Jiacheng Xu, Guoping Wang, Peng-Shuai Wang ·

    ViSculpt:以视觉为中心的代理几何编辑

    arXiv:2608.24169v1 Announce Type: new Abstract: 3D geometry editing is a critical yet labor-intensive part of the graphics pipeline, requiring artists to translate creative intent into precise operations in complex professional software. Large language models (LLMs) have shown pr…

  9. arXiv cs.CV TIER_1 English(EN) · Yun He, Kelin Yu, Matthias Zwicker ·

    SceneOrchestra: 通过完整的工具调用轨迹生成实现高效的代理式三维场景合成

    arXiv:2604.19907v2 Announce Type: replace Abstract: Recent agentic frameworks for 3D scene synthesis have advanced realism and diversity by integrating heterogeneous generation and editing tools. These tools are organized into workflows orchestrated by an off-the-shelf LLM. Curre…

  10. arXiv cs.CV TIER_1 English(EN) · Yun He, Francesco Pittaluga, Ziyu Jiang, Matthias Zwicker, Manmohan Chandraker, Zaid Tasneem ·

    LangDriveCTRL:使用多模态代理进行自然语言可控驾驶场景编辑

    arXiv:2512.17445v3 Announce Type: replace Abstract: LangDriveCTRL is a natural-language-controllable framework for editing real-world driving videos to synthesize diverse traffic scenarios. It represents each video as an explicit 3D scene graph, decomposing the scene into a stati…

  11. arXiv cs.CV TIER_1 English(EN) · Xiujin Liu, Tianyu Yang, Yilun Zhao, Xiangliang Zhang ·

    DesignAgent3D:通过类似设计师的多模态推理进行交互式3D场景编辑

    arXiv:2608.21438v1 Announce Type: new Abstract: Text guided 3D scene editing provides an intuitive interface for modifying reconstructed environments, but remains difficult because natural language design requests are often semantically underspecified and must be grounded in clut…

  12. dev.to — MCP tag TIER_1 English(EN) · Hamza ·

    Spline V2:AI驱动的3D编辑器,支持MCP Server用于Claude代码和Agent工作流

    <p><em>Originally published at <a href="https://tekmag.thsite.top/spline-v2-ai-powered-3d-editor-with-mcp-server-for-claude-code-and-agent-workflows/" rel="noopener noreferrer">https://tekmag.thsite.top/spline-v2-ai-powered-3d-editor-with-mcp-server-for-claude-code-and-agent-work…