this is the epic story of a group of talented digital artists trying to overcame daily technical challenges to achieve incredibly photorealistic projects of monsters and aliens
” In this video, I utilized artificial intelligence to generate an animated music video for the song Canvas by Resonate. This tool allows anyone to generate beautiful images using only text as the input. My question was, what if I used song lyrics as input to the AI, can I make perfect music synchronized videos automatically with the push of a button? Let me know how you think the AI did in this visual interpretation of the song.
After getting caught up in the excitement around DALL·E2 (latest and greatest AI system, it’s INSANE), I searched for any way I could use similar image generation for music synchronization. Since DALL·E2 is not available to the public yet, my search led me to VQGAN + CLIP (Vector Quantized Generative Adversarial Network and Contrastive Language–Image Pre-training), before settling more specifically on Disco Diffusion V5.2 Turbo. If you don’t know what any of these words or acronyms mean, don’t worry, I was just as confused when I first started learning about this technology. I believe we’re reaching a turning point where entire industries are about to shift in reaction to this new process (which is essentially magic!).
Reproduced from a rare original copy, the book features over 165 highly-detailed scans of the legendary art by José Luis García-López, with an introduction by Paul Levitz, former president of DC Comics.
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.
Most software around us today are decent at accurately displaying colors. Processing of colors is another story unfortunately, and is often done badly.
To understand what the problem is, let’s start with an example of three ways of blending green and magenta:
Perceptual blend – A smooth transition using a model designed to mimic human perception of color. The blending is done so that the perceived brightness and color varies smoothly and evenly.
Linear blend – A model for blending color based on how light behaves physically. This type of blending can occur in many ways naturally, for example when colors are blended together by focus blur in a camera or when viewing a pattern of two colors at a distance.
sRGB blend – This is how colors would normally be blended in computer software, using sRGB to represent the colors.
Let’s look at some more examples of blending of colors, to see how these problems surface more practically. The examples use strong colors since then the differences are more pronounced. This is using the same three ways of blending colors as the first example.
Instead of making it as easy as possible to work with color, most software make it unnecessarily hard, by doing image processing with representations not designed for it. Approximating the physical behavior of light with linear RGB models is one easy thing to do, but more work is needed to create image representations tailored for image processing and human perception.
Note: In Foundry’s Nuke, the software will map 18% gray to whatever your center f/stop is set to in the viewer settings (f/8 by default… change that to EV by following the instructions below).
You can experiment with this by attaching an Exposure node to a Constant set to 0.18, setting your viewer read-out to Spotmeter, and adjusting the stops in the node up and down. You will see that a full stop up or down will give you the respective next value on the aperture scale (f8, f11, f16 etc.).
One stop doubles or halves the amount or light that hits the filmback/ccd, so everything works in powers of 2.
So starting with 0.18 in your constant, you will see that raising it by a stop will give you .36 as a floating point number (in linear space), while your f/stop will be f/11 and so on.
If you set your center stop to 0 (see below) you will get a relative readout in EVs, where EV 0 again equals 18% constant gray.
In other words. Setting the center f-stop to 0 means that in a neutral plate, the middle gray in the macbeth chart will equal to exposure value 0. EV 0 corresponds to an exposure time of 1 sec and an aperture of f/1.0.
This will set the sun usually around EV12-17 and the sky EV1-4 , depending on cloud coverage.
To switch Foundry’s Nuke’s SpotMeter to return the EV of an image, click on the main viewport, and then press s, this opens the viewer’s properties. Now set the center f-stop to 0 in there. And the SpotMeter in the viewport will change from aperture and fstops to EV.
“Memory colors are colors that are universally associated with specific objects, elements or scenes in our environment. They are the colors that we expect to see in specific situations: these colors are based on our expectation of how certain objects should look based on our past experiences and memories.
For instance, we associate specific hues, saturation and brightness values with human skintones and a slight variation can significantly affect the way we perceive a scene.
Similarly, we expect blue skies to have a particular hue, green trees to be a specific shade and so on.
Memory colors live inside of our brains and we often impose them onto what we see. By considering them during the grading process, the resulting image will be more visually appealing and won’t distract the viewer from the intended message of the story. Even a slight deviation from memory colors in a movie can create a sense of discordance, ultimately detracting from the viewer’s experience.”
To measure the contrast ratio you will need a light meter. The process starts with you measuring the main source of light, or the key light.
Get a reading from the brightest area on the face of your subject. Then, measure the area lit by the secondary light, or fill light. To make sense of what you have just measured you have to understand that the information you have just gathered is in F-stops, a measure of light. With each additional F-stop, for example going one stop from f/1.4 to f/2.0, you create a doubling of light. The reverse is also true; moving one stop from f/8.0 to f/5.6 results in a halving of the light.
import math,sys
def Exposure2Intensity(exposure):
exp = float(exposure)
result = math.pow(2,exp)
print(result)
Exposure2Intensity(0)
def Intensity2Exposure(intensity):
inarg = float(intensity)
if inarg == 0:
print("Exposure of zero intensity is undefined.")
return
if inarg < 1e-323:
inarg = max(inarg, 1e-323)
print("Exposure of negative intensities is undefined. Clamping to a very small value instead (1e-323)")
result = math.log(inarg, 2)
print(result)
Intensity2Exposure(0.1)
Why Exposure?
Exposure is a stop value that multiplies the intensity by 2 to the power of the stop. Increasing exposure by 1 results in double the amount of light.
Artists think in “stops.” Doubling or halving brightness is easy math and common in grading and look-dev. Exposure counts doublings in whole stops:
+1 stop = ×2 brightness
−1 stop = ×0.5 brightness
This gives perceptually even controls across both bright and dark values.
Why Intensity?
Intensity is linear. It’s what render engines and compositors expect when:
Summing values
Averaging pixels
Multiplying or filtering pixel data
Use intensity when you need the actual math on pixel/light data.
Formulas (from your Python)
Intensity from exposure: intensity = 2**exposure
Exposure from intensity: exposure = log₂(intensity)
Guardrails:
Intensity must be > 0 to compute exposure.
If intensity = 0 → exposure is undefined.
Clamp tiny values (e.g. 1e−323) before using log₂.
Use Exposure (stops) when…
You want artist-friendly sliders (−5…+5 stops)
Adjusting look-dev or grading in even stops
Matching plates with quick ±1 stop tweaks
Tweening brightness changes smoothly across ranges
Use Intensity (linear) when…
Storing raw pixel/light values
Multiplying textures or lights by a gain
Performing sums, averages, and filters
Feeding values to render engines expecting linear data
Examples
+2 stops → 2**2 = 4.0 (×4)
+1 stop → 2**1 = 2.0 (×2)
0 stop → 2**0 = 1.0 (×1)
−1 stop → 2**(−1) = 0.5 (×0.5)
−2 stops → 2**(−2) = 0.25 (×0.25)
Intensity 0.1 → exposure = log₂(0.1) ≈ −3.32
Rule of thumb
Think in stops (exposure) for controls and matching. Compute in linear (intensity) for rendering and math.
When collecting hdri make sure the data supports basic metadata, such as:
Iso
Aperture
Exposure time or shutter time
Color temperature
Color space Exposure value (what the sensor receives of the sun intensity in lux)
7+ brackets (with 5 or 6 being the perceived balanced exposure)
In image processing, computer graphics, and photography, high dynamic range imaging (HDRI or just HDR) is a set of techniques that allow a greater dynamic range of luminances (a Photometry measure of the luminous intensity per unit area of light travelling in a given direction. It describes the amount of light that passes through or is emitted from a particular area, and falls within a given solid angle) between the lightest and darkest areas of an image than standard digital imaging techniques or photographic methods. This wider dynamic range allows HDR images to represent more accurately the wide range of intensity levels found in real scenes ranging from direct sunlight to faint starlight and to the deepest shadows.
The two main sources of HDR imagery are computer renderings and merging of multiple photographs, which in turn are known as low dynamic range (LDR) or standard dynamic range (SDR) images. Tone Mapping (Look-up) techniques, which reduce overall contrast to facilitate display of HDR images on devices with lower dynamic range, can be applied to produce images with preserved or exaggerated local contrast for artistic effect. Photography
In photography, dynamic range is measured in Exposure Values (in photography, exposure value denotes all combinations of camera shutter speed and relative aperture that give the same exposure. The concept was developed in Germany in the 1950s) differences or stops, between the brightest and darkest parts of the image that show detail. An increase of one EV or one stop is a doubling of the amount of light.
The human response to brightness is well approximated by a Steven’s power law, which over a reasonable range is close to logarithmic, as described by the Weber�Fechner law, which is one reason that logarithmic measures of light intensity are often used as well.
HDR is short for High Dynamic Range. It’s a term used to describe an image which contains a greater exposure range than the “black” to “white” that 8 or 16-bit integer formats (JPEG, TIFF, PNG) can describe. Whereas these Low Dynamic Range images (LDR) can hold perhaps 8 to 10 f-stops of image information, HDR images can describe beyond 30 stops and stored in 32 bit images.
Chroma Key Green, the color of green screens is also known as Chroma Green and is valued at approximately 354C in the Pantone color matching system (PMS).
Chroma Green can be broken down in many different ways. Here is green screen green as other values useful for both physical and digital production:
Green Screen as RGB Color Value: 0, 177, 64
Green Screen as CMYK Color Value: 81, 0, 92, 0
Green Screen as Hex Color Value: #00b140
Green Screen as Websafe Color Value: #009933
Chroma Key Green is reasonably close to an 18% gray reflectance.
Illuminate your green screen with an uniform source with less than 2/3 EV variation.
The level of brightness at any given f-stop should be equivalent to a 90% white card under the same lighting.
Ethan Roffler I recently had the honor of interviewing this VFX genius and gained great insight into what it takes to work in the entertainment industry. Keep in mind, these questions are coming from an artist’s perspective but can be applied to any creative individual looking for some wisdom from a professional. So grab a drink, sit back, and enjoy this fun and insightful conversation.
Ethan To start, I just wanted to say thank you so much for taking the time for this interview!
Daniele My pleasure. When I started my career I struggled to find help. Even people in the industry at the time were not that helpful. Because of that, I decided very early on that I was going to do exactly the opposite. I spend most of my weekends talking or helping students. ;)
Ethan That’s awesome! I have also come across the same struggle! Just a heads up, this will probably be the most informal interview you’ll ever have haha! Okay, so let’s start with a small introduction!
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.
