Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Thanks for your excellent work! We have added a link to preprocessed datasets included various conventional surface reconstruction datasets (DTU, BlendedMVS, MobileBrick) as well as some novel view synthetic datasets (nerf_synthetic, nero_synthetic, NSVF_synthetic, refnerf_synthetic). The synthetic datasets encompass challenging scenarios such as low-texture regions, reflective surfaces, and complex geometries. This diverse collection will allow us to thoroughly evaluate the robustness and performance of gaussian-opacity-fields, particularly in handling difficult cases.
The images and ground truth poses for the DTU dataset are obtained from NeuS. For BlendedMVS and MobileBrick, the data is sourced from their respective original repositories: https://github.com/YoYo000/BlendedMVS and https://github.com/ActiveVisionLab/MobileBrick. After extracting the data from these sources, we can directly evaluate the mesh by following the instructions provided in the corresponding original repositories.