Dream-to-Recon:基于单图像的扩散深度蒸馏的单目三维重建
Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images
AI总结:
本文提出Dream-to-Recon方法,利用预训练二维扩散模型和深度预测模型从单张图像生成合成几何,蒸馏前馈重建模型,在KITTI-360和Waymo数据集上达到或超越多视图监督方法,尤其擅长动态场景。
摘要:
从单张图像进行体积场景重建对于自动驾驶和机器人等广泛应用至关重要。近年来的体积重建方法取得了令人瞩目的成果,但通常需要昂贵的三维真实标注或多视图监督。我们提出利用预训练的二维扩散模型和深度预测模型,从单张图像生成合成场景几何。随后,该合成几何可用于蒸馏一个前馈场景重建模型。我们在具有挑战性的KITTI-360和Waymo数据集上的实验表明,我们的方法能够匹配或超越使用多视图监督的最先进基线,并提供了独特优势,例如在动态场景方面。
英文摘要:
Volumetric scene reconstruction from a single image is crucial for a broad range of applications like autonomous driving and robotics. Recent volumetric reconstruction methods achieve impressive results, but generally require expensive 3D ground truth or multi-view supervision. We propose to leverage pre-trained 2D diffusion models and depth prediction models to generate synthetic scene geometry from a single image. This can then be used to distill a feed-forward scene reconstruction model. Our experiments on the challenging KITTI-360 and Waymo datasets demonstrate that our method matches or outperforms state-of-the-art baselines that use multi-view supervision, and offers unique advantages, for example regarding dynamic 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。