This paper presents an introduction to the color pipelines behind modern feature-film visual-effects and animation.
Authored by Jeremy Selan, and reviewed by the members of the VES Technology Committee including Rob Bredow, Dan Candela, Nick Cannon, Paul Debevec, Ray Feeney, Andy Hendrickson, Gautham Krishnamurti, Sam Richards, Jordan Soles, and Sebastian Sylwan.
One problem with sRGB is that in a gradient between blue and white, it becomes a bit purple in the middle of the transition. That’s because sRGB really isn’t created to mimic how the eye sees colors; rather, it is based on how CRT monitors work. That means it works with certain frequencies of red, green, and blue, and also the non-linear coding called gamma. It’s a miracle it works as well as it does, but it’s not connected to color perception. When using those tools, you sometimes get surprising results, like purple in the gradient.
There were also attempts to create simple models matching human perception based on XYZ, but as it turned out, it’s not possible to model all color vision that way. Perception of color is incredibly complex and depends, among other things, on whether it is dark or light in the room and the background color it is against. When you look at a photograph, it also depends on what you think the color of the light source is. The dress is a typical example of color vision being very context-dependent. It is almost impossible to model this perfectly.
I based Oklab on two other color spaces, CIECAM16 and IPT. I used the lightness and saturation prediction from CIECAM16, which is a color appearance model, as a target. I actually wanted to use the datasets used to create CIECAM16, but I couldn’t find them.
IPT was designed to have better hue uniformity. In experiments, they asked people to match light and dark colors, saturated and unsaturated colors, which resulted in a dataset for which colors, subjectively, have the same hue. IPT has a few other issues but is the basis for hue in Oklab.
In the Munsell color system, colors are described with three parameters, designed to match the perceived appearance of colors: Hue, Chroma and Value. The parameters are designed to be independent and each have a uniform scale. This results in a color solid with an irregular shape. The parameters are designed to be independent and each have a uniform scale. This results in a color solid with an irregular shape. Modern color spaces and models, such as CIELAB, Cam16 and Björn Ottosson own Oklab, are very similar in their construction.
By far the most used color spaces today for color picking are HSL and HSV, two representations introduced in the classic 1978 paper “Color Spaces for Computer Graphics”. HSL and HSV designed to roughly correlate with perceptual color properties while being very simple and cheap to compute.
Today HSL and HSV are most commonly used together with the sRGB color space.
One of the main advantages of HSL and HSV over the different Lab color spaces is that they map the sRGB gamut to a cylinder. This makes them easy to use since all parameters can be changed independently, without the risk of creating colors outside of the target gamut.
The main drawback on the other hand is that their properties don’t match human perception particularly well.
Reconciling these conflicting goals perfectly isn’t possible, but given that HSV and HSL don’t use anything derived from experiments relating to human perception, creating something that makes a better tradeoff does not seem unreasonable.
With this new lightness estimate, we are ready to look into the construction of Okhsv and Okhsl.
A number of problems in computer vision and related fields would be mitigated if camera spectral sensitivities were known. As consumer cameras are not designed for high-precision visual tasks, manufacturers do not disclose spectral sensitivities. Their estimation requires a costly optical setup, which triggered researchers to come up with numerous indirect methods that aim to lower cost and complexity by using color targets. However, the use of color targets gives rise to new complications that make the estimation more difficult, and consequently, there currently exists no simple, low-cost, robust go-to method for spectral sensitivity estimation that non-specialized research labs can adopt. Furthermore, even if not limited by hardware or cost, researchers frequently work with imagery from multiple cameras that they do not have in their possession.
To provide a practical solution to this problem, we propose a framework for spectral sensitivity estimation that not only does not require any hardware (including a color target), but also does not require physical access to the camera itself. Similar to other work, we formulate an optimization problem that minimizes a two-term objective function: a camera-specific term from a system of equations, and a universal term that bounds the solution space.
Different than other work, we utilize publicly available high-quality calibration data to construct both terms. We use the colorimetric mapping matrices provided by the Adobe DNG Converter to formulate the camera-specific system of equations, and constrain the solutions using an autoencoder trained on a database of ground-truth curves. On average, we achieve reconstruction errors as low as those that can arise due to manufacturing imperfections between two copies of the same camera. We provide predicted sensitivities for more than 1,000 cameras that the Adobe DNG Converter currently supports, and discuss which tasks can become trivial when camera responses are available.
In video terms gamut is normally related to as the full range of colours and brightness that can be either captured or displayed.
Generally speaking all color gamuts recommendations are trying to define a reasonable level of color representation based on available technology and hardware. REC-601 represents the old TVs. REC-709 is currently the most distributed solution. P3 is mainly available in movie theaters and is now being adopted in some of the best new 4K HDR TVs. Rec2020 (a wider space than P3 that improves on visibke color representation) and ACES (the full coverage of visible color) are other common standards which see major hardware development these days.
To compare and visualize different solution (across video and printing solutions), most developers use the CIE color model chart as a reference.
The CIE color model is a color space model created by the International Commission on Illumination known as the Commission Internationale de l’Elcairage (CIE) in 1931. It is also known as the CIE XYZ color space or the CIE 1931 XYZ color space.
This chart represents the first defined quantitative link between distributions of wavelengths in the electromagnetic visible spectrum, and physiologically perceived colors in human color vision. Or basically, the range of color a typical human eye can perceive through visible light.
Note that while the human perception is quite wide, and generally speaking biased towards greens (we are apes after all), the amount of colors available through nature, generated through light reflection, tend to be a much smaller section. This is defined by the Pointer’s Chart.
In short. Color gamut is a representation of color coverage, used to describe data stored in images against available hardware and viewer technologies.
The CIE 1931 standard has been replaced by a CIE 1976 standard. Below we can see the significance of this.
People have observed that the biggest issue with CIE 1931 is the lack of uniformity with chromaticity, the three dimension color space in rectangular coordinates is not visually uniformed.
The CIE 1976 (also called CIELUV) was created by the CIE in 1976. It was put forward in an attempt to provide a more uniform color spacing than CIE 1931 for colors at approximately the same luminance
The CIE 1976 standard colour space is more linear and variations in perceived colour between different people has also been reduced. The disproportionately large green-turquoise area in CIE 1931, which cannot be generated with existing computer screens, has been reduced.
If we move from CIE 1931 to the CIE 1976 standard colour space we can see that the improvements made in the gamut for the “new” iPad screen (as compared to the “old” iPad 2) are more evident in the CIE 1976 colour space than in the CIE 1931 colour space, particularly in the blues from aqua to deep blue.
Despite its age, CIE 1931, named for the year of its adoption, remains a well-worn and familiar shorthand throughout the display industry. CIE 1931 is the primary language of customers. When a customer says that their current display “can do 72% of NTSC,” they implicitly mean 72% of NTSC 1953 color gamut as mapped against CIE 1931.
The human eye perceives half scene brightness not as the linear 50% of the present energy (linear nature values) but as 18% of the overall brightness. We are biased to perceive more information in the dark and contrast areas. A Macbeth chart helps with calibrating back into a photographic capture into this “human perspective” of the world.
In photography, painting, and other visual arts, middle gray or middle grey is a tone that is perceptually about halfway between black and white on a lightness scale in photography and printing, it is typically defined as 18% reflectance in visible light
Light meters, cameras, and pictures are often calibrated using an 18% gray card[4][5][6] or a color reference card such as a ColorChecker. On the assumption that 18% is similar to the average reflectance of a scene, a grey card can be used to estimate the required exposure of the film.
Of all the pigments that have been banned over the centuries, the color most missed by painters is likely Lead White.
This hue could capture and reflect a gleam of light like no other, though its production was anything but glamorous. The 17th-century Dutch method for manufacturing the pigment involved layering cow and horse manure over lead and vinegar. After three months in a sealed room, these materials would combine to create flakes of pure white. While scientists in the late 19th century identified lead as poisonous, it wasn’t until 1978 that the United States banned the production of lead white paint.
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:
Physically-based shading means leaving behind phenomenological models, like the Phong shading model, which are simply built to “look good” subjectively without being based on physics in any real way, and moving to lighting and shading models that are derived from the laws of physics and/or from actual measurements of the real world, and rigorously obey physical constraints such as energy conservation.
For example, in many older rendering systems, shading models included separate controls for specular highlights from point lights and reflection of the environment via a cubemap. You could create a shader with the specular and the reflection set to wildly different values, even though those are both instances of the same physical process. In addition, you could set the specular to any arbitrary brightness, even if it would cause the surface to reflect more energy than it actually received.
In a physically-based system, both the point light specular and the environment reflection would be controlled by the same parameter, and the system would be set up to automatically adjust the brightness of both the specular and diffuse components to maintain overall energy conservation. Moreover you would want to set the specular brightness to a realistic value for the material you’re trying to simulate, based on measurements.
Physically-based lighting or shading includes physically-based BRDFs, which are usually based on microfacet theory, and physically correct light transport, which is based on the rendering equation (although heavily approximated in the case of real-time games).
It also includes the necessary changes in the art process to make use of these features. Switching to a physically-based system can cause some upsets for artists. First of all it requires full HDR lighting with a realistic level of brightness for light sources, the sky, etc. and this can take some getting used to for the lighting artists. It also requires texture/material artists to do some things differently (particularly for specular), and they can be frustrated by the apparent loss of control (e.g. locking together the specular highlight and environment reflection as mentioned above; artists will complain about this). They will need some time and guidance to adapt to the physically-based system.
On the plus side, once artists have adapted and gained trust in the physically-based system, they usually end up liking it better, because there are fewer parameters overall (less work for them to tweak). Also, materials created in one lighting environment generally look fine in other lighting environments too. This is unlike more ad-hoc models, where a set of material parameters might look good during daytime, but it comes out ridiculously glowy at night, or something like that.
Here are some resources to look at for physically-based lighting in games:
SIGGRAPH 2013 Physically Based Shading Course, particularly the background talk by Naty Hoffman at the beginning. You can also check out the previous incarnations of this course for more resources.
And of course, I would be remiss if I didn’t mention Physically-Based Rendering by Pharr and Humphreys, an amazing reference on this whole subject and well worth your time, although it focuses on offline rather than real-time rendering.
The trigger phrase is “equirectangular 360 degree panorama”. I would avoid saying “spherical projection” since that tends to result in non-equirectangular spherical images.
Image resolution should always be a 2:1 aspect ratio. 1024 x 512 or 1408 x 704 work quite well and were used in the training data. 2048 x 1024 also works.
I suggest using a weight of 0.5 – 1.5. If you are having issues with the image generating too flat instead of having the necessary spherical distortion, try increasing the weight above 1, though this could negatively impact small details of the image. For Flux guidance, I recommend a value of about 2.5 for realistic scenes.
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.
