1st Place Solution for ICCV 2023 OmniObject3D Challenge: Sparse-View Reconstruction
This addresses the challenge of 3D reconstruction from sparse views for computer vision applications, but it is incremental as it builds on existing methods like Pixel-NeRF.
The paper tackled the problem of novel view synthesis and surface reconstruction from only a few posed images, achieving first place in the ICCV 2023 OmniObject3D Challenge with a PSNR of 25.44614.
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.