In this report, we present the 1st place solution for ICCV 2023 OmniObject3D
Challenge: Sparse-View Reconstruction. The challenge aims to evaluate
approaches for novel view synthesis and surface reconstruction using only a few
posed images of each object. We utilize Pixel-NeRF as the basic model, and
apply depth supervision as well as coarse-to-fine positional encoding. The
experiments demonstrate the effectiveness of our approach in improving
sparse-view reconstruction quality. We ranked first in the final test with a
PSNR of 25.44614.

本文提出了在 ICCV 2023 OmniObject3D Challenge 的稀疏视图重建中获得第一名解决方案。我们利用 Pixel-NeRF 作为基本模型，并应用深度监督和粗到精的位置编码。实验证明了我们的方法在改善稀疏视图重建质量方面的有效性，我们在最终测试中以 25.44614 的 PSNR 排名第一。

ICCV 2023 OmniObject3D 挑战赛第 1 名解决方案：稀疏视图重建

1st Place Solution for ICCV 2023 OmniObject3D Challenge: Sparse-View  Reconstruction

This report provides an overview of the challenge hosted at the OpenSUN3D
Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with
ICCV 2023. The goal of this workshop series is to provide a platform for
exploration and discussion of open-vocabulary 3D scene understanding tasks,
including but not limited to segmentation, detection and mapping. We provide an
overview of the challenge hosted at the workshop, present the challenge
dataset, the evaluation methodology, and brief descriptions of the winning
methods. For additional details, please see
this https URL

该报告提供了 OpenSUN3D 举办的 Open-Vocabulary 3D 场景理解挑战赛的概述，包括分割、检测和映射等任务，并介绍了挑战赛的数据集、评估方法和获奖方法的简要描述。