The book “Computer Vision Metrics: Survey, Taxonomy, and Analysis” is available for free download as a PDF or other formats. Go to the “Source Code/Downloads” tab in the middle of the page and work your way through the labyrinth. Also, you can get the Kindle edition for free. From my pretty limited knowledge of image processing, this looks like a useful survey book, running through common techniques and pointing to relevant references. Me, I was interested in segmentation algorithms for non-photorealistic rendering, and it has a reasonable section all about this topic.
You are currently browsing the archive for the Resources category.
If you’re a member of SIGGRAPH, one perk is that you have access to the ACM Digital Library’s graphics related content. The SIGGRAPH benefits document notes:
- Access to all ACM SIGGRAPH related content in the ACM Digital Library (This includes SIGGRAPH, SIGGRAPH Asia, and about 20 or more small conferences)
I learned where to find the list of 20 small conferences, it’s here. And it’s not 20, it’s over 100. Admittedly, some of these symposia were run just once or twice, but I appreciate the access nonetheless. It’s a big world! Wandering through this list is fascinating, and a little nostalgic – “Ahh, remember when that topic was a hot new trend? Whatever happened to it?” Honestly, it’s exciting to see so many areas where graphics has an effect. If I had students looking for research topics in graphics and no strong preference about what area they wanted to explore, I’d point them at this page as a source for inspiration, dry as it looks.
I asked about this list because I had a problem accessing some NPAR papers through the DL. As usual, I drove around the damage by using Google Scholar and finding the papers I wanted elsewhere, for free. To the ACM’s credit, they responded to my query about whether I was supposed to have access to NPAR, since I had access in the past. I was indeed, and they fixed the DL the next day. So, the takeaway is that if you find you don’t have access and think you should, let the ACM know at [email protected].
Finally, I found this just peculiar, on this page:
Seriously? The secrets of the teapot cannot be fully revealed? Who (the heck) would not give reprint permission? Or was it just a matter of someone being unreachable, and the default being the text couldn’t be reprinted? There’s a story there…
I spent an inordinate amount of time just updating the books page at this site. It hadn’t been done for about two years – I can finally check this task off the list. It took awhile tracking down related websites for each book, especially Google Books samples, which can be quite large and worthwhile for some books. I also cleaned out older volumes from the listing and updated the recommendations list.
From what I can tell – and please do tell me if I’ve missed anything – beyond API books (OpenGL and DirectX) and the GPU Pro series, there have been very few new graphics books since 2013. The major release has been a new edition of Computer Graphics: Principles and Practice. There was also The CUDA Handbook, which is somewhat graphics related but not strictly so. I also included The HDRI Handbook; even though it’s more a user’s guide, it does have some good bits about the theory of tone mapping and much else, in an area that can use more coverage. I don’t bother listing the many books about Unity 3D, the Unreal Engine, etc., since those truly fall in the area of guides.
Anyway, that’s all until SIGGRAPH, when I can take a look at what else is out there.
Really, the title says it all, the book GPU Pro 5 is shipping. Sadly, there’s no “Look Inside” for the book on Amazon; I’ll hope they at least put the Table of Contents there. You can find a rough Table of Contents on the CRC site; rough in that you can’t see the number of pages for each article. A few articles are quite lengthy: Physically Base Area Lights is 34 pages long, Hi-Z Screen-Space Cone-Traced Reflections is an incredible 44. The rest are in the 10-20 page range.
You can get a taste of the book at the GPU Pro blog, it has previews of a large number of the articles. At $70 this is not a casual purchase, but if you’re a practitioner and just one article saves you 2 hours, the book’s more than paid for itself.
The short version is go see this page here.
I’m collaborating on a little hobby project with Andrew Glassner. It involves paint spectra, so we were hunting down a spectrometer. We’d heard good things about ColorMunki, though it’s pricey for a hobby project. There’s now even a $40 spectrometer from Public Labs; they’re located a few miles from where I live.
Andrew decided to ask Golden Artist Colors, Inc., if they had spectra available for their paints. Happily, they did and agreed to release these for free, noting that “spectra are spectra”. This saves us a lot of grunt work and expense, which is great. I felt so good about them that I decided to make a page about their dataset so that researchers and developers could also benefit from it.
Andrew Glassner has made an 8 week course about the graphics language Processing. The first half of the course is free; if you find you like it, the second half is just $25. Even if you don’t want to take the course, you should watch the 2.5 minute video at the site – beware, it may change your mind. The video gives a sense of the power of Processing and some of the wonderful things you can do with it. My small bit of experience with the language showed me it’s a nice way to quickly display and fiddle around with all sorts of graphical ideas. While I dabbled for a week, Andrew used it for half a decade and has made some fascinating programs. Any language that can have such a terrible name and still thrive in so many ways definitely has something going for it.
guest post by Patrick Cozzi, @pjcozzi.
This isn’t as crazy as it sounds: WebGL has a chance to become the graphics API of choice for real-time graphics research. Here’s why I think so.
An interactive demo is better than a video.
WebGL allows us to embed demos in a website, like the demo for The Compact YCoCg Frame Buffer by Pavlos Mavridis and Georgios Papaioannou. A demo gives readers a better understanding than a video alone, allows them to reproduce performance results on their hardware, and enables them to experiment with debug views like the demo for WebGL Deferred Shading by Sijie Tian, Yuqin Shao, and me. This is, of course, true for a demo written with any graphics API, but WebGL makes the barrier-to-entry very low; it runs almost everywhere (iOS is still holding back the floodgates) and only requires clicking on a link. Readers and reviewers are much more likely to check it out.
WebGL runs on desktop and mobile.
Android devices now have pretty good support for WebGL. This allows us to write the majority of our demo once and get performance numbers for both desktop and mobile. This is especially useful for algorithms that will have different performance implications due to differences in GPU architectures, e.g., early-z vs. tile-based, or network bandwidth, e.g., streaming massive models.
WebGL is starting to expose modern GPU features.
WebGL is based on OpenGL ES 2.0 so it doesn’t expose features like query timers, compute shaders, uniform buffers, etc. However, with some WebGL 2 (based on ES 3.0) features being exposed as extensions, we are getting access to more GPU features like instancing and multiple render targets. Given that OpenGL ES 3.1 will be released this year with compute shaders, atomics, and image load/store, we can expect WebGL to follow. This will allow compute-shader-based research in WebGL, an area where I expect we’ll continue to see innovation. In addition, with NVIDIA Tegra K1, we see OpenGL 4.4 support on mobile, which could ultimately mean more features exposed by WebGL to keep pace with mobile.
Some graphics research areas, such as animation, don’t always need access to the latest GPU features and instead just need a way to visualization their results. Even many of the latest JCGT papers on rendering can be implemented with WebGL and the extensions it exposes today (e.g., “Weighted Blended Order-Independent Transparency“). On the other hand, some research will explore the latest GPU features or use features only available to languages with pointers, for example, using persistent-mapped buffers in Approaching Zero Driver Overhead by Cass Everitt, Graham Sellers, John McDonald, and Tim Foley.
WebGL is faster to develop with.
Check out the WebGL Report to see what extensions your browser supports. If it meets the needs for your next research project, give it a try!
Here we go:
- Four free mini-courses from SIGGRAPH on computer graphics, how nice is that? First one’s by Andrew Glassner, one of my favorite lecturers.
- GPU Pro 5 teaser articles are up for viewing. I look forward to the day when we can just get the dang book immediately – really, I have to wait until March? The world could end before then, and then where would I be?
- GPU Pro 6 has a call for participation. Do it!
- A great illusion at Shadertoy, and a new shading illusion (I hope two links here makes up for the two separate GPU Pro listings).
- A little dated, but a thorough rundown of various global illumination related effects on the GPU.
- Some worthwhile arguments against doing a z-buffer prepass. I tend to agree (and of course YMMV), as doing a good sort goes a long way towards getting the benefits.
- And since I haven’t been posting half as much as I’d like, here’s an amazing collection of graphics blogs, that should keep y’all satisfied.
Here are a few cool things I noticed and seem appropriate to post today.
First, this person is doing cool real-life procedural texturing. Or I should say, is really covering up, since we know the aliens are the ones who are really making these.
The Graphics Codex now has three sample PDFs available for free download, to give you a sense of what’s in the app/book. Find the links in the right-hand column.
The Christmas Experiments gives 24 little graphical presents, scroll down to make them appear. I haven’t opened them all up yet, as I was working backward and only got as far as this one, which is lovely and interactive.
With the holidays upon us, it’s time to hack! Well, a little bit. I spent a fair bit of time improving my transforms demo, folding in comments from others and my own ideas. Many thanks to all who sent me suggestions (and anyone’s welcome to send more). I like one subtle feature now: if the blue test point is clipped, it turns red and clipping is also noted in the transforms themselves.
The feature I like the most is that which shows the frustum. Run the demo and select “Show frustum: depths”. Admire that the scene is rendered on the view frustum’s near plane. Rotate the camera around (left mouse) until it’s aligned to a side view of the view frustum. You’ll see the near and far plane depths (colored), and some equally spaced depth planes in between (in terms of NDC and Z-depth values, not in terms of world coordinates).
Now play with the near and far plane depths under “Camera manipulation” (open that menu by clicking on the arrow to the left of the word “Camera”). This really shows the effect of moving the near place close to the object, evening out the distribution of the plane depths. Here’s an example:
The mind-bender part of this new viewport feature is that if you rotate the camera, you’re of course rotating the frustum in the opposite direction in the viewport, which holds the view of the scene steady and shows the camera’s movement. My mind is constantly seeing the frustum “inverted”, as it wants both directions to be in the same direction, I think. I even tried modeling the tip where the eye is located, to give a “front” for the eye position, but that doesn’t help much. Probably a fully-modeled eyeball would be a better tipoff, but that’s way more work than I want to put into this.
You can try lots of other things; dolly is done with the mouse wheel (or middle mouse up and down), pan with the right mouse. All the code is downloadable from my github repository.
Click on image for a larger, readable version.