OCH3R: 以对象为中心的全局3D重建
OCH3R: Object-Centric Holistic 3D Reconstruction
AI总结：
OCH3R提出一种统一框架，从单张RGB图像实现以对象为中心的全局3D重建，通过单次前向传递预测所有对象实例的6D位姿和详细3D重建，提升效率与鲁棒性。
摘要：
面向计算机视觉中的对象中心场景理解，现有方法多依赖多阶段流程，先用预训练分割器提取个体对象，再进行逐对象3D重建。此类方法计算成本高、易受分割误差影响且在场景复杂度增加时表现不佳。本文提出OCH3R，一种统一的以对象为中心的全局3D重建框架。OCH3R通过单次前向传递同时预测所有对象实例的6D位姿和详细3D重建。关键思想是基于transformer架构，预测像素级属性，包括基于CLIP的类别嵌入、度量深度、归一化对象坐标（NOCS）以及每个对象的固定数量3D高斯分布。为了监督这些高斯重建，将它们转换为标准空间并利用预测的6D位姿与预先渲染的标准地面真相对齐，避免了昂贵的每张图像高斯标签生成。在标准室内基准上，OCH3R在单目深度估计、开放词汇语义分割和仅RGB的类别级6D位姿估计方面均取得最佳性能，同时生成高保真且可编辑的逐对象重建。关键的是，推理过程完全前馈，且与对象数量无关，从而在拥挤场景中比传统多阶段流程快数个数量级。
英文摘要：
Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that first apply pre-trained segmentors to extract individual objects, followed by per-object 3D reconstruction. Such methods are computationally expensive, fragile to segmentation errors, and scale poorly with scene complexity. We introduce OCH3R, a unified framework for Object-Centric Holistic 3D Reconstruction from a single RGB image. OCH3R performs one forward pass to simultaneously predict all object instances with their 6D poses and detailed 3D reconstructions. The key idea is a transformer architecture that predicts per-pixel attributes, including CLIP-based category embeddings, metric depth, normalized object coordinates (NOCS), and a fixed number of 3D Gaussians representing each object. To supervise these Gaussian reconstructions, we transform them into canonical space using the predicted 6D poses and align them with pre-rendered canonical ground truth, avoiding costly per-image Gaussian label generation. On standard indoor benchmarks, OCH3R achieves state-of-the-art performance across monocular depth estimation, open-vocabulary semantic segmentation, and RGB-only category-level 6D pose estimation, while producing high-fidelity, editable per-object reconstructions. Crucially, inference is fully feed-forward and scales independently of the number of objects, offering orders-of-magnitude speedups over conventional multi-stage pipelines in cluttered scenes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
