The coolest thing here might be the speed: for a given scene RenderFormer takes 0.0760 seconds while Blender Cycles takes 3.97 seconds (or 12.05 secs at a higher setting), while retaining a 0.9526 Structural Similarity Index Measure (0-1 where 1 is an identical image). See tables 2 and 1 in the paper.<p>This could possibly enable higher quality instant render previews for 3D designers in web or native apps using on-device transformer models.<p>Note the timings above were on an A100 with an unoptimized PyTorch version of the model. Obviously the average user's GPU is much less powerful, and for 3D designers it might be still powerful enough to see significant speedups over traditional rendering. Or for a web-based system it could even connect to A100s on the backend and stream the images to the browser.<p>Limitations are that it's not fully accurate especially as scene complexity scales, e.g. with shadows of complex shapes (plus I imagine particles or strands), so the final renders will probably still be done traditionally to avoid any of the nasty visual artifacts common in many AI-generated images/videos today. But who knows, it might be "good enough" and bring enough of a speed increase to justify use by big animation studios who need to render full movie-length previews to use for music, story review, etc etc.
Deep learning is also very successfully used for denoising of global illumination rendered images [1]. In this approach, traditional raytracing algorithm quickly computes rough global illumination of the scene, and neural network is used to remove noise from the output. .<p>[1] <a href="https://www.openimagedenoise.org" rel="nofollow">https://www.openimagedenoise.org</a>
With every graphics paper it's important to think about what you don't see. Here there are barely any polygons, low resolution, no textures, no motion blur, no depth of field and there are some artifacts in the animation.<p>It's interesting research but to put it in perspective this is using modern GPUs to make images that look like what was being done with 1/1,000,000 the computation 30 years ago.
I found it odd that none of the examples showed anything behind the camera. I'm not sure if that's a limitation of the approach or an oversight in creating examples. What I do know is that when we're talking about reflections and lighting what's behind the camera is pretty important.
Forgive my ignorance: are these scenes rendered based on how a scene is expected to be rendered? If so, why would we use this over more direct methods (since I assume this is not faster than direct methods)?
I have a friend that works on physically based renderers in the film industry and has also done research in the area. Always love hearing stories and explanations about how things get done in this industry.<p>What companies are hiring such talent at the moment? Have the AI companies also been hiring rendering engineers for creating training environments?<p>If you are looking to hire an experienced research and industry rendering engineer i am happy to connect you since my friend is not on social media but has been putting out feelers.
Very cool research! I really like these applications of transformers to domains other than text. It seems it would work well with any domains where the input is sequential and those input tokens relate to each other. I'm looking forward to more research in this space.<p>HN what do you think are interesting non-text domains where transformers would be well suited?
This is a stellar and interesting idea: train a transformer to turn a scene description set of triangles into a 2d array of pixels, which happens to look like the pixels a global illumination renderer would output from the same scene.<p>That this works at all shouldn’t be shocking after the last five years of research, but I still find it pretty profound. That transformer architecture sure is versatile.<p>Anyway, crazy fast, close to blender’s rendering output, what looks like a 1B parameter model? Not sure if it’s fp16 or 32, but it’s a 2GB file, what’s not to like? I’d like to see some more ‘realistic’ scenes demoed, but hey, I can download this and run it on my Mac to try it whenever I like.
The bitter lesson strikes again… now for graphics rendering. Nerfs had a ray tracing prior, and Gaussian splats had some raster prior. This just… throws it all away. No priors, no domain knowledge, just data and attention.
This is the way.