Radiant Foam: Real-Time Differentiable Ray Tracing

212 points by w-m 5 months ago | 23 comments
  • thih9 5 months ago
    At the end of the video there is a non-pinhole camera demo; could someone explain what exactly is different about this camera?

    I.e. what exactly the video is showing? And what would the video look like if that was a pinhole camera?

    • kvark 5 months ago
      In pinhole cameras, straight lines look straight. That's what a regular projection matrix gives you with rasterization. With non-pinhole cameras, straight lines look curved. You can't rasterize this directly. 3D Gaussian splats have an issue with this, addressed by methods like ray tracing. It's very useful to train on non-pinhole cameras, because in real world they can capture a wider field of view.
      • markisus 5 months ago
        In Gaussian Splatting, a first order approximation takes ellipsoids in camera space to ellipses in image space. This works ok for pigeonhole cameras where straight lines remain straight and more generally conic sections are taken to other conic sections. For high distortion models like fisheye, this approximation probably breaks. However this method presumably does not rely on approximation since it is ray traced.
        • jedbrooke 5 months ago
          looks like it’s some sort of fisheye camera with a super wide fov. it might be simulating rays bending due to lens effects. a pinhole camera could just look “normal” ie straight lines stay straight (except for horizon convergence perspective effects)
        • momojo 5 months ago
          > This algorithm is much more efficient than typical ray tracing acceleration methods that rely on hierarchical acceleration structures with logarithmic query complexity.

          !?

          This is a wild claim to just slip in. Can anyone expand?

          • niederman 5 months ago
            It's faster because there are only a constant number of other faces in a given cell to check to find where the ray exits. Then you can just traverse from cell to cell in this way, without using hierarchical bounding box checks like you normally would.
            • momojo 5 months ago
              So its not tree based? Is it a graph traversal of sorts?
            • TinkersW 5 months ago
              Em? Seems reasonable, ray tracing a BVH is inherently slow AF because it diverges like mad(SIMD no like).
            • xnx 5 months ago
              How is Google using all these amazing radiant field techniques they're developing?
              • lairv 5 months ago
                TBH only one author out of four has a Google affiliation, and their personal webpage [1] says "part-time (20%) staff research scientist at Google DeepMind", so it's a stretch to call this a "Google technique". I notice that this is a common thing when discussing research paper, people associate it with the first company name they can find in the affiliations

                [1] https://theialab.ca/

                • dwallin 5 months ago
                  For one, I’ve seen interactive Gaussian Splatting interior flythroughs in the Google Maps app.
                  • mlsu 5 months ago
                    Pure conjecture: relighting in Pixel phones. I don't think they have too many AR-like products. I'm surprised so much of this research is coming out of Google and not Meta.
                    • xnx 5 months ago
                      I'm a little surprised Google hasn't included lidar into their Pixel phones (even after including and dropping some oddball stuff like Soli) to support some of these radiance field / photogrammetry techniques. I guess the <2.5% market share of Pixel phones wouldn't encourage any third parties with bothering to develop for lidar on Android.
                    • catapart 5 months ago
                      I have no idea, but given their stock of pictures of the entire earth (via google maps), I have some ideas about what I HOPE they would use this tech for.
                      • wongarsu 5 months ago
                        And Google Maps/Google Earth have a long history of trying to create 3d views using all kinds of techniques, from manual modeling to radar satellite data.
                      • CyberDildonics 5 months ago
                        How do you know they're amazing until you've used them yourself?
                        • TuringTourist 5 months ago
                          By being amazed when observing it, one can conclude that a thing is amazing.
                          • macawfish 5 months ago
                            They do look amazing
                            • CyberDildonics 5 months ago
                              You must have more faith in research papers than I do. Every single one I've actually used has had significant flaws that are glossed over by what isn't being shown or said.