1st Place Solution for ICCV 2023 OmniObject3D Challenge: Sparse-View Reconstruction
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 8 of its 9 references that are in the map. First posted on arXiv 16 Apr 2024.
Builds on
8 of 9 references.
References · 8
- 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
- 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
- 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
- 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
- 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
- 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
- 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
Built on by
Citing papers per year: 2025: 1.
1 paper.