arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2509.02474cs.GRcs.CVcs.LG
收藏

Unifi3D:统一框架下用于生成与重建的3D表示研究

Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework

Intel Corporation(英特尔公司)

Nina Wiedemann, Sainan Liu, Quentin Leboutet, Katelyn Gao, Benjamin Ummenhofer, Michael Paulitsch, Kai Yuan

AI总结:

针对3D表示碎片化的问题,提出Unifi3D统一评估框架,从多维度对比各类3D表示在生成与重建中的表现,总结流水线最佳实践,证明联合评估的必要性,为3D模型选型提供参考。

摘要:

随着文本和图像生成技术的快速发展,研究重心日益转向3D生成领域。与图像领域成熟的基于像素的表示不同,3D表示仍呈现多样化且碎片化的特点,涵盖体素网格、神经辐射场(NeRF)、有符号距离函数(SDF)、点云或八叉树等多种方法,每种方法各有优劣。本研究提出了一个统一评估框架,用于评估3D表示在重建和生成任务中的性能。我们从质量、计算效率和泛化性能多个维度对这些表示进行对比。除了标准的模型基准测试,我们的实验还旨在总结3D生成流水线全流程的最佳实践,包括预处理、网格重建、自编码器压缩以及生成环节。研究结果表明,重建误差会显著影响整体性能,凸显了联合评估生成与重建的必要性。我们的研究结论可为各类应用选择合适的3D模型提供参考,推动3D生成领域更稳健、更具应用针对性的解决方案的开发。该框架的代码可在https://github.com/isl-org/unifi3d获取。

英文摘要:

Following rapid advancements in text and image generation, research has increasingly shifted towards 3D generation. Unlike the well-established pixel-based representation in images, 3D representations remain diverse and fragmented, encompassing a wide variety of approaches such as voxel grids, neural radiance fields, signed distance functions, point clouds, or octrees, each offering distinct advantages and limitations. In this work, we present a unified evaluation framework designed to assess the performance of 3D representations in reconstruction and generation. We compare these representations based on multiple criteria: quality, computational efficiency, and generalization performance. Beyond standard model benchmarking, our experiments aim to derive best practices over all steps involved in the 3D generation pipeline, including preprocessing, mesh reconstruction, compression with autoencoders, and generation. Our findings highlight that reconstruction errors significantly impact overall performance, underscoring the need to evaluate generation and reconstruction jointly. We provide insights that can inform the selection of suitable 3D models for various applications, facilitating the development of more robust and application-specific solutions in 3D generation. The code for our framework is available at https://github.com/isl-org/unifi3d.

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。

↑