# DIRECT：通过分解视觉代理实现直接3D感知物体插入

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-04 08:00
- AIHOT 分数：50
- AIHOT 链接：https://aihot.virxact.com/items/cmq4wvmt402gaslt2aql8b0hg
- 原文链接：https://arxiv.org/abs/2606.06601

## AI 摘要

提出DIRECT框架，实现姿态可控的物体插入。该方法将插入条件分解为三个互补组件：参考物体外观引导、用户调整的3D代理几何引导、目标背景上下文引导，通过分开注入避免特征纠缠，同时保留参考外观、遵循指定姿态并适配场景。还引入自动化数据构建管道提升训练数据多样性与质量。实验表明，DIRECT在几何可控性和视觉质量上均优于此前方法。

## 正文

Object insertion aims to seamlessly composite a reference object into a specified region of a background image. Recent diffusion-based methods achieve high visual quality but formulate insertion as a simple 2D inpainting task, providing no explicit control over the object's 3D pose and limiting their practical applicability. We propose DIRECT (Decomposed Injection for Reference Composition and Target-integration), a novel framework that integrates interactive pose manipulation with high-fidelity 2D image synthesis to enable pose-controllable object insertion. Our method decomposes the insertion conditions into three complementary components: appearance guidance capturing visual details from the reference object, geometry guidance derived from the user-adjusted 3D proxy, and context guidance from the target background. By injecting them through separate pathways, DIRECT avoids feature entanglement and simultaneously preserves reference appearance, follows the user-specified pose, and adapts the object to the target scene. We also introduce an automated data construction pipeline to improve the diversity and quality of training data. Experiments show that DIRECT outperforms previous methods in both geometric controllability and visual quality.