Search found 45 matches

by papaboo
Thu Oct 01, 2015 12:13 pm
Forum: General Development
Topic: Separate GPU compute kernels vs. a single GPU kernel
Replies: 10
Views: 10636

Re: Separate GPU compute kernels vs. a single GPU kernel

Well that does make profiling a bit tricky. ;) Volume rendering and surface rendering can still use more or less the same primitive operations as in OptiX though as far as I remember. See Wenzel Jakob's thesis for the specific. But I haven't tried out volume rendering yet though, so my memory might ...
by papaboo
Thu Oct 01, 2015 8:16 am
Forum: General Development
Topic: Separate GPU compute kernels vs. a single GPU kernel
Replies: 10
Views: 10636

Re: Separate GPU compute kernels vs. a single GPU kernel

It really depends a lot on your use case, but separating the ray generation program and the gamma correction post process pass from a traversal-and-shading kernel is almost bound to give you zero improvements. The kernels are so small that anything you could gain by having better occupancy is probab...
by papaboo
Thu Jul 23, 2015 7:33 am
Forum: General Development
Topic: Question about normal mapping in Ray tracingIt looks like al
Replies: 7
Views: 8193

Re: Question about normal mapping in Ray tracingIt looks lik

A question to all of you out there using normal maps. How do you handle rays that intersect the surface on the front side, but are on the backside of the bumped normal?
by papaboo
Thu Jul 23, 2015 5:52 am
Forum: General Development
Topic: pbrt-v3 source code now available
Replies: 23
Views: 24418

Re: pbrt-v3 source code now available

You could always implement them as very well documented integrators and add them to the source code, then they wouldn't even have to be ready for the release. For VCM/UPS though there is already three papers and SmallVCM. If you've read and understood PBRT, then that should be enough to get anyone s...
by papaboo
Thu Jul 02, 2015 2:15 pm
Forum: General Development
Topic: pbrt-v3 source code now available
Replies: 23
Views: 24418

Re: pbrt-v3 source code now available

I'm with Koiava on this. Generally I find it much easier to return both sample and pdf as a single entity. It just makes it clear that you need to take the pdf into account. The only exception is when we can sample something uniformly and the pdf is the same for all samples. In some of those cases w...
by papaboo
Thu Jul 02, 2015 9:51 am
Forum: Visuals, Tools, Demos & Sources
Topic: Visionaray Ray Tracing Framework
Replies: 11
Views: 26435

Re: Visionaray Ray Tracing Framework

Thanks for feedback and the link to foveated ray tracing. Haven't read that yet, so now I have an excuse for sitting outside in the sun and do some reading. :) I would consider photon mapping a 'soft' baking approach, since there is a preprocess step, but it's really quick. A rebake is increadibly f...
by papaboo
Wed Jul 01, 2015 12:07 pm
Forum: Visuals, Tools, Demos & Sources
Topic: Visionaray Ray Tracing Framework
Replies: 11
Views: 26435

Re: Visionaray Ray Tracing Framework

Sounds really cool. Slightly off-topic: In the integration with VR do you do any GI effects or is it Whitted only? If you do GI (which I of course hope :) ) can you then share any thoughts on the subject? PT would be the obvious quick and dirty solution, but it produces so much noise that it can't w...
by papaboo
Tue May 26, 2015 7:56 am
Forum: General Development
Topic: algorithm choice
Replies: 7
Views: 7090

Re: algorithm choice

Regarding general BVH quality On Quality Metrics of Bounding Volume Hierarchies might be an interesting read.
by papaboo
Tue May 26, 2015 7:54 am
Forum: General Development
Topic: algorithm choice
Replies: 7
Views: 7090

Re: algorithm choice

That's true for any acceleration structure though.
by papaboo
Tue May 19, 2015 12:05 pm
Forum: General Development
Topic: algorithm choice
Replies: 7
Views: 7090

Re: algorithm choice

OptiX TrBVH is probably the current state-of-the-art for GPUs. What I don't know though is if they build it on top of a 'normal' BVH or an MBVH.

Either way. The optimization of treelet restructuring should be applicable to both, so maybe you can try it out. ;)