BundleRecon: Ray Bundle-Based 3D Neural Reconstruction
This is an incremental improvement for neural rendering methods, addressing a specific bottleneck in multi-view 3D reconstruction.
The paper tackles the problem of neural implicit multi-view reconstruction by proposing BundleRecon, which uses a bundle of rays to sample patches of pixels instead of single rays, improving reconstruction quality by incorporating neighboring pixel information.
With the growing popularity of neural rendering, there has been an increasing number of neural implicit multi-view reconstruction methods. While many models have been enhanced in terms of positional encoding, sampling, rendering, and other aspects to improve the reconstruction quality, current methods do not fully leverage the information among neighboring pixels during the reconstruction process. To address this issue, we propose an enhanced model called BundleRecon. In the existing approaches, sampling is performed by a single ray that corresponds to a single pixel. In contrast, our model samples a patch of pixels using a bundle of rays, which incorporates information from neighboring pixels. Furthermore, we design bundle-based constraints to further improve the reconstruction quality. Experimental results demonstrate that BundleRecon is compatible with the existing neural implicit multi-view reconstruction methods and can improve their reconstruction quality.