1. Watch every frame of raw footage twice. On the second time, take notes. If you don’t do this and try to start developing a scene premature, then it’s a big disservice to yourself and to the director, actors and production crew.
2. Nurture the relationships with the director. You are the secondary person in the relationship. Be calm and continually offer solutions. Get the main intention of the film as soon as possible from the director.
3. Organize your media so that you can find any shot instantly.
4. Factor in extra time for renders, exports, errors and crashes.
5. Attempt edits and ideas that shouldn’t work. It just might work. Until you do it and watch it, you won’t know. Don’t rule out ideas just because they don’t make sense in your mind.
6. Spend more time on your audio. It’s the glue of your edit. AUDIO SAVES EVERYTHING. Create fluid and seamless audio under your video.
7. Make cuts for the scene, but always in context for the whole film. Have a macro and a micro view at all times.
” 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!).
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.
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.
It lets you load any .cube LUT right in your browser, see the RGB curves, and use a split view on the Granger Test Image to compare the original vs. LUT-applied version in real time — perfect for spotting hue shifts, saturation changes, and contrast tweaks.
This page compares images rendered in Arnold using spectral rendering and different sets of colourspace primaries: Rec.709, Rec.2020, ACES and DCI-P3. The SPD data for the GretagMacbeth Color Checker are the measurements of Noburu Ohta, taken from Mansencal, Mauderer and Parsons (2014) colour-science.org.
In general, when light interacts with matter, a complicated light-matter dynamic occurs. This interaction depends on the physical characteristics of the light as well as the physical composition and characteristics of the matter.
That is, some of the incident light is reflected, some of the light is transmitted, and another portion of the light is absorbed by the medium itself.
A BRDF describes how much light is reflected when light makes contact with a certain material. Similarly, a BTDF (Bi-directional Transmission Distribution Function) describes how much light is transmitted when light makes contact with a certain material
It is difficult to establish exactly how far one should go in elaborating the surface model. A truly complete representation of the reflective behavior of a surface might take into account such phenomena as polarization, scattering, fluorescence, and phosphorescence, all of which might vary with position on the surface. Therefore, the variables in this complete function would be:
incoming and outgoing angle incoming and outgoing wavelength incoming and outgoing polarization (both linear and circular) incoming and outgoing position (which might differ due to subsurface scattering) time delay between the incoming and outgoing light ray
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!
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.
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.
