“I used GPT-4 to describe itself. Then I used its description to generate an image, a video based on this image and a soundtrack.
Tools I used: GPT-4, Midjourney, Kaiber AI, Mubert, RunwayML
This is the description I used that GPT-4 had of itself as a prompt to text-to-image, image-to-video, and text-to-music. I put the video and sound together in RunwayML.
GPT-4 described itself as: “Imagine a sleek, metallic sphere with a smooth surface, representing the vast knowledge contained within the model. The sphere emits a soft, pulsating glow that shifts between various colors, symbolizing the dynamic nature of the AI as it processes information and generates responses. The sphere appears to float in a digital environment, surrounded by streams of data and code, reflecting the complex algorithms and computing power behind the AI”
About 576 megapixels for the entire field of view.
Consider a view in front of you that is 90 degrees by 90 degrees, like looking through an open window at a scene. The number of pixels would be:
90 degrees * 60 arc-minutes/degree * 1/0.3 * 90 * 60 * 1/0.3 = 324,000,000 pixels (324 megapixels).
At any one moment, you actually do not perceive that many pixels, but your eye moves around the scene to see all the detail you want. But the human eye really sees a larger field of view, close to 180 degrees. Let’s be conservative and use 120 degrees for the field of view. Then we would see:
The Manuka rendering architecture has been designed in the spirit of the classic reyes rendering architecture. In its core, reyes is based on stochastic rasterisation of micropolygons, facilitating depth of field, motion blur, high geometric complexity,and programmable shading.
This is commonly achieved with Monte Carlo path tracing, using a paradigm often called shade-on-hit, in which the renderer alternates tracing rays with running shaders on the various ray hits. The shaders take the role of generating the inputs of the local material structure which is then used bypath sampling logic to evaluate contributions and to inform what further rays to cast through the scene.
Over the years, however, the expectations have risen substantially when it comes to image quality. Computing pictures which are indistinguishable from real footage requires accurate simulation of light transport, which is most often performed using some variant of Monte Carlo path tracing. Unfortunately this paradigm requires random memory accesses to the whole scene and does not lend itself well to a rasterisation approach at all.
Manuka is both a uni-directional and bidirectional path tracer and encompasses multiple importance sampling (MIS). Interestingly, and importantly for production character skin work, it is the first major production renderer to incorporate spectral MIS in the form of a new ‘Hero Spectral Sampling’ technique, which was recently published at Eurographics Symposium on Rendering 2014.
Manuka propose a shade-before-hit paradigm in-stead and minimise I/O strain (and some memory costs) on the system, leveraging locality of reference by running pattern generation shaders before we execute light transport simulation by path sampling, “compressing” any bvh structure as needed, and as such also limiting duplication of source data.
The difference with reyes is that instead of baking colors into the geometry like in Reyes, manuka bakes surface closures. This means that light transport is still calculated with path tracing, but all texture lookups etc. are done up-front and baked into the geometry.
The main drawback with this method is that geometry has to be tessellated to its highest, stable topology before shading can be evaluated properly. As such, the high cost to first pixel. Even a basic 4 vertices square becomes a much more complex model with this approach.
Manuka use the RenderMan Shading Language (rsl) for programmable shading [Pixar Animation Studios 2015], but we do not invoke rsl shaders when intersecting a ray with a surface (often called shade-on-hit). Instead, we pre-tessellate and pre-shade all the input geometry in the front end of the renderer.
This way, we can efficiently order shading computations to sup-port near-optimal texture locality, vectorisation, and parallelism. This system avoids repeated evaluation of shaders at the same surface point, and presents a minimal amount of memory to be accessed during light transport time. An added benefit is that the acceleration structure for ray tracing (abounding volume hierarchy, bvh) is built once on the final tessellated geometry, which allows us to ray trace more efficiently than multi-level bvhs and avoids costly caching of on-demand tessellated micropolygons and the associated scheduling issues.
For the shading reasons above, in terms of AOVs, the studio approach is to succeed at combining complex shading with ray paths in the render rather than pass a multi-pass render to compositing.
For the Spectral Rendering component. The light transport stage is fully spectral, using a continuously sampled wavelength which is traced with each path and used to apply the spectral camera sensitivity of the sensor. This allows for faithfully support any degree of observer metamerism as the camera footage they are intended to match as well as complex materials which require wavelength dependent phenomena such as diffraction, dispersion, interference, iridescence, or chromatic extinction and Rayleigh scattering in participating media.
As opposed to the original reyes paper, we use bilinear interpolation of these bsdf inputs later when evaluating bsdfs per pathv ertex during light transport4. This improves temporal stability of geometry which moves very slowly with respect to the pixel raster
In terms of the pipeline, everything rendered at Weta was already completely interwoven with their deep data pipeline. Manuka very much was written with deep data in mind. Here, Manuka not so much extends the deep capabilities, rather it fully matches the already extremely complex and powerful setup Weta Digital already enjoy with RenderMan. For example, an ape in a scene can be selected, its ID is available and a NUKE artist can then paint in 3D say a hand and part of the way up the neutral posed ape.
We called our system Manuka, as a respectful nod to reyes: we had heard a story froma former ILM employee about how reyes got its name from how fond the early Pixar people were of their lunches at Point Reyes, and decided to name our system after our surrounding natural environment, too. Manuka is a kind of tea tree very common in New Zealand which has very many very small leaves, in analogy to micropolygons ina tree structure for ray tracing. It also happens to be the case that Weta Digital’s main site is on Manuka Street.
In the retina, photoreceptors, bipolar cells, and horizontal cells work together to process visual information before it reaches the brain. Here’s how each cell type contributes to vision:
In HD we often refer to the range of available colors as a color gamut. Such a color gamut is typically plotted on a two-dimensional diagram, called a CIE chart, as shown in at the top of this blog. Each color is characterized by its x/y coordinates.
Good enough for government work, perhaps. But for HDR, with its higher luminance levels and wider color, the gamut becomes three-dimensional.
For HDR the color gamut therefore becomes a characteristic we now call the color volume. It isn’t easy to show color volume on a two-dimensional medium like the printed page or a computer screen, but one method is shown below. As the luminance becomes higher, the picture eventually turns to white. As it becomes darker, it fades to black. The traditional color gamut shown on the CIE chart is simply a slice through this color volume at a selected luminance level, such as 50%.
Three different color volumes—we still refer to them as color gamuts though their third dimension is important—are currently the most significant. The first is BT.709 (sometimes referred to as Rec.709), the color gamut used for pre-UHD/HDR formats, including standard HD.
The largest is known as BT.2020; it encompasses (roughly) the range of colors visible to the human eye (though ET might find it insufficient!).
Between these two is the color gamut used in digital cinema, known as DCI-P3.
sRGB: A standard “web”/computer-display RGB color space defined by IEC 61966-2-1. It’s used for most monitors, cameras, printers, and the vast majority of images on the Internet.
Rec. 709: An HD-video color space defined by ITU-R BT.709. It’s the go-to standard for HDTV broadcasts, Blu-ray discs, and professional video pipelines.
Why they exist
sRGB: Ensures consistent colors across different consumer devices (PCs, phones, webcams).
Rec. 709: Ensures consistent colors across video production and playback chains (cameras → editing → broadcast → TV).
What you’ll see
On your desktop or phone, images tagged sRGB will look “right” without extra tweaking.
On an HDTV or video-editing timeline, footage tagged Rec. 709 will display accurate contrast and hue on broadcast-grade monitors.
Size. Mr. White (Harvey Keitel) on the right. Focus. He’s one of the two objects in focus. Lighting. Mr. White is large and in focus and Mr. Pink (Steve Buscemi) is highlighted by a shaft of light. Color. Both are black and white but the read on Mr. White’s shirt now really stands out.
Black-body radiation is the type of electromagnetic radiation within or surrounding a body in thermodynamic equilibrium with its environment, or emitted by a black body (an opaque and non-reflective body) held at constant, uniform temperature. The radiation has a specific spectrum and intensity that depends only on the temperature of the body.
A black-body at room temperature appears black, as most of the energy it radiates is infra-red and cannot be perceived by the human eye. At higher temperatures, black bodies glow with increasing intensity and colors that range from dull red to blindingly brilliant blue-white as the temperature increases.
The Black Body Ultraviolet Catastrophe Experiment
In photography, color temperature describes the spectrum of light which is radiated from a “blackbody” with that surface temperature. A blackbody is an object which absorbs all incident light — neither reflecting it nor allowing it to pass through.
The Sun closely approximates a black-body radiator. Another rough analogue of blackbody radiation in our day to day experience might be in heating a metal or stone: these are said to become “red hot” when they attain one temperature, and then “white hot” for even higher temperatures. Similarly, black bodies at different temperatures also have varying color temperatures of “white light.”
Despite its name, light which may appear white does not necessarily contain an even distribution of colors across the visible spectrum.
Although planets and stars are neither in thermal equilibrium with their surroundings nor perfect black bodies, black-body radiation is used as a first approximation for the energy they emit. Black holes are near-perfect black bodies, and it is believed that they emit black-body radiation (called Hawking radiation), with a temperature that depends on the mass of the hole.
RASTERIZATION Rasterisation (or rasterization) is the task of taking the information described in a vector graphics format OR the vertices of triangles making 3D shapes and converting them into a raster image (a series of pixels, dots or lines, which, when displayed together, create the image which was represented via shapes), or in other words “rasterizing” vectors or 3D models onto a 2D plane for display on a computer screen.
For each triangle of a 3D shape, you project the corners of the triangle on the virtual screen with some math (projective geometry). Then you have the position of the 3 corners of the triangle on the pixel screen. Those 3 points have texture coordinates, so you know where in the texture are the 3 corners. The cost is proportional to the number of triangles, and is only a little bit affected by the screen resolution.
In computer graphics, a raster graphics orbitmap image is a dot matrix data structure that represents a generally rectangular grid of pixels (points of color), viewable via a monitor, paper, or other display medium.
With rasterization, objects on the screen are created from a mesh of virtual triangles, or polygons, that create 3D models of objects. A lot of information is associated with each vertex, including its position in space, as well as information about color, texture and its “normal,” which is used to determine the way the surface of an object is facing.
Computers then convert the triangles of the 3D models into pixels, or dots, on a 2D screen. Each pixel can be assigned an initial color value from the data stored in the triangle vertices.
Further pixel processing or “shading,” including changing pixel color based on how lights in the scene hit the pixel, and applying one or more textures to the pixel, combine to generate the final color applied to a pixel.
The main advantage of rasterization is its speed. However, rasterization is simply the process of computing the mapping from scene geometry to pixels and does not prescribe a particular way to compute the color of those pixels. So it cannot take shading, especially the physical light, into account and it cannot promise to get a photorealistic output. That’s a big limitation of rasterization.
There are also multiple problems:
If you have two triangles one is behind the other, you will draw twice all the pixels. you only keep the pixel from the triangle that is closer to you (Z-buffer), but you still do the work twice.
The borders of your triangles are jagged as it is hard to know if a pixel is in the triangle or out. You can do some smoothing on those, that is anti-aliasing.
You have to handle every triangles (including the ones behind you) and then see that they do not touch the screen at all. (we have techniques to mitigate this where we only look at triangles that are in the field of view)
Transparency is hard to handle (you can’t just do an average of the color of overlapping transparent triangles, you have to do it in the right order)
RAY CASTING It is almost the exact reverse of rasterization: you start from the virtual screen instead of the vector or 3D shapes, and you project a ray, starting from each pixel of the screen, until it intersect with a triangle.
The cost is directly correlated to the number of pixels in the screen and you need a really cheap way of finding the first triangle that intersect a ray. In the end, it is more expensive than rasterization but it will, by design, ignore the triangles that are out of the field of view.
You can use it to continue after the first triangle it hit, to take a little bit of the color of the next one, etc… This is useful to handle the border of the triangle cleanly (less jagged) and to handle transparency correctly.
RAYTRACING
Same idea as ray casting except once you hit a triangle you reflect on it and go into a different direction. The number of reflection you allow is the “depth” of your ray tracing. The color of the pixel can be calculated, based off the light source and all the polygons it had to reflect off of to get to that screen pixel.
The easiest way to think of ray tracing is to look around you, right now. The objects you’re seeing are illuminated by beams of light. Now turn that around and follow the path of those beams backwards from your eye to the objects that light interacts with. That’s ray tracing.
Ray tracing is eye-oriented process that needs walking through each pixel looking for what object should be shown there, which is also can be described as a technique that follows a beam of light (in pixels) from a set point and simulates how it reacts when it encounters objects.
Compared with rasterization, ray tracing is hard to be implemented in real time, since even one ray can be traced and processed without much trouble, but after one ray bounces off an object, it can turn into 10 rays, and those 10 can turn into 100, 1000…The increase is exponential, and the the calculation for all these rays will be time consuming.
Historically, computer hardware hasn’t been fast enough to use these techniques in real time, such as in video games. Moviemakers can take as long as they like to render a single frame, so they do it offline in render farms. Video games have only a fraction of a second. As a result, most real-time graphics rely on the another technique called rasterization.
PATH TRACING Path tracing can be used to solve more complex lighting situations. Path tracing is a type of ray tracing. When using path tracing for rendering, the rays only produce a single ray per bounce. The rays do not follow a defined line per bounce(to a light, for example), but rather shoot off in a random direction. The path tracing algorithm then takes a random sampling of all of the rays to create the final image. This results in sampling a variety of different types of lighting.
When a ray hits a surface it doesn’t trace a path to every light source, instead it bounces the ray off the surface and keeps bouncing it until it hits a light source or exhausts some bounce limit. It then calculates the amount of light transferred all the way to the pixel, including any color information gathered from surfaces along the way. It then averages out the values calculated from all the paths that were traced into the scene to get the final pixel color value.
It requires a ton of computing power and if you don’t send out enough rays per pixel or don’t trace the paths far enough into the scene then you end up with a very spotty image as many pixels fail to find any light sources from their rays. So when you increase the the samples per pixel, you can see the image quality becomes better and better.
Ray tracing tends to be more efficient than path tracing. Basically, the render time of a ray tracer depends on the number of polygons in the scene. The more polygons you have, the longer it will take. Meanwhile, the rendering time of a path tracer can be indifferent to the number of polygons, but it is related to light situation: If you add a light, transparency, translucence, or other shader effects, the path tracer will slow down considerably.
DISCLAIMER – Links and images on this website may be protected by the respective owners’ copyright. All data submitted by users through this site shall be treated as freely available to share.
