Jump to content

Michael Tetzlaff

Moderators
  • Posts

    39
  • Joined

  • Last visited

  • Days Won

    1

Michael Tetzlaff last won the day on October 26 2024

Michael Tetzlaff had the most liked content!

Recent Profile Visitors

The recent visitors block is disabled and is not being shown to other users.

Michael Tetzlaff's Achievements

Explorer

Explorer (4/14)

  • Reacting Well Rare
  • Collaborator Rare
  • Conversation Starter Rare
  • First Post Rare
  • One Month Later Rare

Recent Badges

1

Reputation

  1. Yes, the 0.3.25 documentation is the most recent revision of the docs. The 1.0.0 software version should be essentially the same; the main new feature is an improved progress indicator for importing and processing textures.
  2. This thread aggregates various papers and posters on Kintsugi 3D Viewer. Refer also to the parallel thread on Kintsugi 3D Builder. Papers: Lou Brown, Charles Walbridge, and Michael Tetzlaff, “Kintsugi 3D: An Empirically-Based Photogrammetry Production Pipeline,” IS&T Archiving Conference, 2024, pp. 76-80. PDF Tyler Garcia, Zhangchi Lyu, and Michael Tetzlaff, “An Online Model Viewer for Cultural Heritage in Unity 3D,” *IS&T Archiving Conference*, 2022, pp. 50-55. PDF Posters: Kintsugi 3D Viewer: User-Centric Design for Cultural Heritage Accessibility (May 2024)
  3. This thread aggregates various papers and posters on Kintsugi 3D Builder. Refer also to the parallel thread on Kintsugi 3D Viewer. Papers: Lou Brown, Charles Walbridge, and Michael Tetzlaff, “Kintsugi 3D: An Empirically-Based Photogrammetry Production Pipeline,” IS&T Archiving Conference, 2024, pp. 76-80. PDF Michael Tetzlaff, “High-Fidelity Specular SVBRDF Acquisition from Flash Photographs,” IEEE Transactions on Visualization and Computer Graphics (TVCG), vol. 30, no. 4, 2024, pp. 1885-1896. https://ieeexplore.ieee.org/document/10012127 PDF Appendix 1077-2626 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information. Giljoo Nam, Joo Ho Lee, Diego Gutierrez, and Min H. Kim, “Practical SVBRDF Acquisition of 3D Objects with Unstructured Flash Photography,” ACM Transactions on Graphics, vol. 37, no. 6, 2018, pp. 267:1-267:12. https://dl.acm.org/doi/10.1145/3272127.3275017 Michael Tetzlaff, Gary Meyer, and Alex Kautz, “IBRelight: An Image-Based 3D Renderer for Cultural Heritage,” IS&T Archiving Conference, 2018, pp. 93-98. PDF Posters: Kintsugi 3D Builder: User Experience Design and Implementation (May 2024) User Experience of Visualizing Empirically-Based Textures in Kintsugi 3D Builder (December 2024)
  4. Hi Dale, if you're able to send me the dataset in a private email, I can take a look at this in more detail. Is this a Metashape project, I assume? One possibility is that there's a bug in Kintsugi's image undistortion procedure, which I could easily check by running Metashape's undistort export option and comparing.
  5. No, those questions are good. It's helpful to get it documented here on the forums and probably deserves more explicit addressing in the official documentation.
  6. Hi Dale -- typically, we just remove that one from the dataset (disable it in Metashape or Reality Capture) before importing / processing in Kintsugi 3D Builder. For the primary view, you can just select one that is similar to the view that had the Color Checker (we are also working on a better method of handling the reference view for the Color Checker). At some point in the future, maybe we will have a way to disable the photo in Kintsugi directly -- but for now, it needs to be done before importing.
  7. Thanks, Kurt -- we've gotten the same feedback from Mia regarding an option to respect the original orientation, but it's good to hear it from you too to get confirmation and perhaps bump this in priority. We are also working on a process to rotate the primary view in 90 degree increments when used, which I think would also address the use case you're describing. Hopefully we'll have some improvements to the UX along those lines for the primary view / model orientation soon.
  8. It's actually configurable in the settings, but I think by default it's 5 images blended. The tricky thing is that it in theory actually varies by pixel (depending on the focal length of the real camera compared to the virtual camera, it's possible that at extreme angles, the weights and even the views selected would be different -- and this is even more true if you turn relighting on and the normal vector starts playing a role). But I think we could still figure out a way to make it work as for most pixels, with relighting off, the weights and view selection shouldn't be too different.
  9. Hi Kurt, Both of those are great ideas. Currently, the only way to force it to reload all images is to clear the cache under File > Settings > Cache Settings. This will reset all projects, though (which shouldn't really matter apart from some longer loading times assuming all photos are still there). Clearing the cache for just a single project would be a good feature that we could probably implement pretty easily. I'll add that along with the view filtering idea to our backlog.
  10. @sjoerv Ideally, yes. We've used Kintsugi successfully with projects that included photos that did cut off part of the object ( @Charles Walbridge might be able to comment more on that) but there is always a chance of seams if such photos are included (for now, until we have time to implement a better solution for this use case). If you have a dataset where you're seeing issues because of that and are willing to share it, we might be able to use it as a test case for addressing this situation in a future version of Kintsugi.
  11. Interesting -- if you are willing to zip up the project that's causing problems and send it to me, I or one of my students could look into what's causing the problem for the full project import method. And I still need to look at the other dataset you sent me assuming you didn't figure out what the problem was there. It's been on my to-do list but just haven't had the time.
  12. Sounds good -- I'll also add looking into support for Cycles to the backlog. It looks like it might be possible using an Open Shading Language script.
  13. Thanks, Kurt. In the original Metashape project, were there images with the same name and folder but different file extensions? (i.e. IMAGE0001.png and IMAGE0001.jpg in the same directory)? That's my best guess as to the source of the issue -- if you had two capture sessions differentiated only by file extension in the same folder, Kintsugi strips the file extension and tries all recognized extensions in a predetermined (arbitrary) order.
  14. Hi, thanks for trying out Kintsugi 3D! Can I first ask where you're viewing the model in the Kintsugi screenshot? Is it in Kintsugi 3D Viewer, Kintsugi 3D Builder, Sketchfab, Blender, or somewhere else? My first instinct is that looks like it might actually be a shadow being cast by a light source. I might see if you can move the light to see if the line moves. If it is truly baked into the textures, sometimes that can happen when you have a photograph in the input set that cuts off part of the object -- this causes a seam between the part of the object visible in the photo and the part not visible. One temporary solution might be to edit the photo in Photoshop and add an alpha mask that fades to transparent at the edge of the photo if you can identify the image that might be causing this -- Kintsugi 3D Builder will read the alpha channel and decrease the influence of the masked/semi-transparent pixels accordingly. I'd like to eventually have a more robust solution integrated into Kintsugi 3D for scenarios like this.
  15. Thanks for sharing! Glad that was able to resolve the issue, and I agree that the specular count = 4 version looks the best.
×
×
  • Create New...