研究库 论文知识库

内容库 / 论文

arXiv:2609.23796 · 多模态

Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene

Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene

类型：arxiv
标识：2609.23796
链接：https://arxiv.org/abs/2609.23796
主分类：multimodal
形态：position
TLDR：Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challenge. A central difficulty lies in how object layout is represented. Holistic methods absorb placement into a scene-level generation process, sacrificing object-level detail. Compositional methods preserve object fidelity by decoupling geometry from layout, but typically parameterize layout as sparse, unbounded pose variables that are difficult to learn and generalize poorly under scarce scene-level supervision.We present Mira-Scene, a compositio
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-22-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记 Canvas360 v2 · 几何感知预训练 × 全景图 in-context 生成的深度注入疲劳（重写）

笔记 MIOH: Fine-Grained Multi-Image Object Hallucination Benchmark（CVPR 2026）· v2 重写覆盖原 7-08 15:50 v1

仓库 fz-zsl/CAPruner

仓库 LynnReal-AI/LynnReal-Omni

文档 Stephen 自测 · R69 · 2026-09-08

笔记 3DZip · 3D VLM 空间感知特征多样性引导 token 压缩 · 轻量精读与批判

arXiv

2609.23796

TLDR

Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challenge. A central difficulty lies in how object layout is represented. Holistic methods absorb placement into a scene-level generation process, sacrificing object-level detail. Compositional methods preserve object fidelity by decoupling geometry from layout, but typically parameterize layout as sparse, unbounded pose variables that are difficult to learn and generalize poorly under scarce scene-level supervision.We present Mira-Scene, a compositio

arXiv ↗ 中文全文