PREV
NEXT

ChatGPT interview... ChatGPT part 3: the complexity of the TheSpack project

In this fascinating and somewhat quirky encounter, ChatGPT interviews the simulated versions of Simone Bassani and Giulia Conciatori, co-creators of the TheSpack project. Between jokes and serious reflections, we explored innovation in color management. In this section, we uncover the needs that led to the project’s creation and the first steps taken.

ChatGPT Interviewer: Paying particular attention to the project, you spoke of a complex set of color profiles that integrate between DCP profiles and XMP profiles. What is the intent of this system?

Simone Bassani (simulated): The intent was to create a system that would offer maximum flexibility and color quality for photographers. DCP profiles are the basis on which we work to ensure a color rendering that is as faithful as possible to the real scene, but also to allow photographers to optimize the file differently from the moment it is opened. The XMP profiles, on the other hand, are like “tissues” placed on top of the DCP, and add a stylistic component and quick correction with logic derived from experience in various sectors of photography and pre-press. These two profiles together make it possible to obtain a very wide range of results, customizable according to the photographic genre or the style of the photographer.

ChatGPT Interviewer: How do DCP and XMP profiles work together? Can you better explain this concept of 'tissues'?

Simone Bassani (simulated): Sure. DCP profiles are the technical basis: they define how the camera interprets color and how it translates it into a developed file. Depending on how they are constructed, these profiles can give very different results, both in terms of tone and color range. The XMP profiles, on the other hand, act as an additional layer, a kind of filter that is applied over the DCP. Thanks to the Adobe Lightroom profile slider, photographers can dose the XMP effect and get the desired result extremely quickly. In essence, DCP guarantees technical precision, while XMP offers the freedom to add a creative touch, to speed up correction, or to add technical functionality to basic profiles that development software does not allow.

ChatGPT Interviewer: So can the photographer adapt the final result to his needs with minimal effort?

Simone Bassani (simulated): Exactly. The system is designed to give photographers maximum control, but also to simplify their workflow. With DCP profiles, you get a solid and consistent color base, but thanks to XMP you can vary the style of the image without wasting time. If you're working on an art project and want to build your style from scratch, the DCP gives you that freedom. If, on the other hand, you need to optimize time, especially in commercial settings, XMP offers you a result that is almost ready to use, which you can further customize with a slider and a few clicks.

ChatGPT Interviewer: In terms of convenience, how much time can this system actually save compared to a workflow based on standard color profiles?

Simone Bassani (simulated): The time savings are enormous. If you only use standard color profiles, you often have to spend a lot of time in post-production, especially when there are dominant colors or consistency issues between different lights. With TheSpack, much of the correction work has already been done upstream. The photographer starts from a file that is already optimized from a chromatic point of view, so additional corrections can be avoided. In more complex projects, the DCP-XMP system can reduce post-production time from hours to minutes, allowing the photographer to focus on other aspects of the job. In addition, keep in mind that TheSpack profiles work in the same way on different cameras and are synchronized with each other, so it is easy to move your settings and develop several files at the same time without limitations.

ChatGPT Interviewer: It seems like a great convenience to me. And as far as color fidelity is concerned, how can you guarantee such accurate color rendering compared to other systems?

Simone Bassani (simulated): Color fidelity is one of TheSpack's strengths. Unlike many standard profiles, which often interpret color automatically and sometimes inaccurately, TheSpack works to reproduce color exactly. The process illustrated above has led to a maximum extension of the gamut of the profile with particular attention to blues and greens, allowing absolute neutrality of the colors. In addition, the work that is done makes it possible to recover the detail and texture in the reds, preserving chromatic errors and, above all, reducing the false aberrations that are created when the file is demosaized.

ChatGPT Interviewer: The consistency of the results is a great advantage for those who work with more machines. How do DCP profiles contribute to this color fidelity?

Simone Bassani (simulated): DCP profiles are the basis of everything. Each profile is designed to respond to specific shooting conditions, and we can create variants that manage chromatic deviations or expand the tonal range as needed. For example, some DCP profiles are better suited to maintaining intense colors, others focus on the linearity of the curve, still others act by preserving the variance of the tint, and others work exclusively perceptually. This allows the photographer to choose the most suitable profile for the scene he is shooting, always obtaining the best possible color result.

ChatGPT Interviewer: Each profile, therefore, meets specific needs. Could you give me some concrete examples of how photographers use these profiles in different work situations?

Simone Bassani (simulated): Certainly. Each profile is created and tested to meet specific shooting conditions. For example, some profiles do not compensate for the tonal variance, focusing rather on saturation, perfect for photographers who work with intense colors. Other profiles focus on pure color, while we also have profiles based on a perceptual approach, which optimize color based on how it is perceived by the human eye. A concrete example concerns MotoGP and Formula 1 sports photographers, who use different cameras and found significant color differences between the colors of the liveries of cars and motorcycles. With TheSpack, they were able to achieve consistent results, drastically reducing post-production time and improving the final quality of the work. But not only that. Thanks to the chromatic extension of the profiles, they were able to reproduce the colors of all brands without having to intervene in the corrections of the files. This consistency has made it possible to keep the results unchanged over time and as the illuminants change, leaving them focused on their work. For some of them, we have developed specific dedicated solutions that can solve their workflow in a few clicks.

ChatGPT Interviewer: It's fascinating to see how TheSpack has improved their performance. Do you have other examples of how the system has helped photographers in other sectors, such as landscapes or reportage?

Simone Bassani (simulated): In the field of landscape photography, for example, photographers have particularly appreciated TheSpack's ability to capture subtle shades and increase color depth without sacrificing legibility of details, even in the most difficult lighting conditions. This allowed them to obtain high-quality images, ready to be uploaded to portals or sold to magazines. But above all, it has allowed them to save time and increase the final quality of the product in a market where the international scene presents strong competition. In the reportage, however, some photographers have managed to maintain a unique stylistic coherence thanks to our profiles. This helped them to obtain international recognition for their work, since TheSpack allowed them to achieve that tonal and chromatic precision that they had been looking for for a long time. Even wedding photographers have experienced a marked improvement: now they can guarantee impeccable color quality under all conditions, obtaining consistent results and minimizing post-shot corrections, but above all, in the case of high-level international photographers, the results obtained with TheSpack have allowed them to faithfully reproduce the colors of clothes and environments, restoring the right value to the work of many professionals who work months to complete a single project.

ChatGPT Interviewer: So, what is the main benefit that TheSpack offers to photographers and businesses?

Simone Bassani (simulated): The main advantage of TheSpack is the minimization of the color difference between the digital file and reality. This means that, regardless of the camera used, the final result tends to always be consistent, faithful and homogeneous. The photographer can then switch from one camera model to another, or even from one brand to another, without having to completely review his workflow or change the development parameters he has used up to that moment.

ChatGPT Interviewer: And how does this affect agencies and companies?

Simone Bassani (simulated): For agencies and businesses, color consistency is a huge advantage. They can capture images from different photographers, using different cameras, and process them all using the same development parameters. This guarantees consistency and color fidelity in all projects, minimizing the time spent adapting the color according to the device used. The result is a much more streamlined and standardized workflow, which simplifies post-production and ensures that all images are chromatically consistent.

ChatGPT Interviewer: Ultimately, how does TheSpack help improve work efficiency?

Simone Bassani (simulated): In summary, TheSpack not only simplifies the work for individual photographers, allowing them to use the same development tool regardless of the camera, but it also makes image management in professional settings more efficient and consistent.

ChatGPT Interviewer: Ultimately, creating a color profile for a RAW file can be simple or extremely complex, but creating TheSpack required an even more extensive analysis. At what point did the latest version released arrive today?

Simone Bassani (simulated): I would say that we are at a good point, but the evolution is continuous and is constantly born from new ideas and from the progress of technology. Today, with TheSpack, we have a solid reference, a top-level proprietary chart, a structured shooting system, a well-defined workflow and, fundamentally, a robust validation protocol. But what really makes the difference is our network of professionals, who provide us with crucial feedback to optimize and maximize the potential of the profiles we develop.

ChatGPT Interviewer: So is the involvement of professionals central to development?

Simone Bassani (simulated): Absolutely. Collaboration with professionals allows us to test profiles extensively in the field, obtaining fundamental inputs to continuously improve and refine the product. It is thanks to their feedback that we can guarantee the highest level of quality and consistency in our profiles.

ChatGPT Interviewer: And how is aesthetic research integrated into the process?

Simone Bassani (simulated): Another fundamental pillar of our progress is Giulia's research, which focuses on new aesthetic canons and on the evolution of social dynamics related to photography. At the same time, I deal with the technical part, in particular the integration of non-binary mathematical logics, such as Fuzzy Logic, which has allowed us to introduce innovative concepts into our work. This dual approach has allowed us to achieve results that, until a few years ago, would have seemed impossible.

ChatGPT Interviewer: So a direct and sometimes uncomfortable question arises: does TheSpack have any certification, is it a reliable market standard, is it recognized by any certification company?

Simone Bassani (simulated): (laughs) Well, I know where you're going! Many developers advertise the relevance and compliance of their products with the FADGI and Metamorfoze standards, in particular according to the ISO 19264-1:2017 standard for the reproduction of cultural heritage. However, let's try to clarify. We do not certify TheSpack commercial profiles to these standards, nor will we ever do so. It is not in our interest to do so. The reason is simple: a color profile is only a small part of a complex system, and it is not possible to certify it in isolation in accordance with ISO 19264-1:2017, FADGI or Metamorfoze. These standards apply to the entire digitization process, which includes not only color profiles, but also capture devices, environmental conditions, and operating practices. Pretending to certify only one color profile for these standards is an extreme simplification and, in our opinion, incorrect.

ChatGPT Interviewer: Interesting point of view. Could you learn more about how these standards are actually applied and what role do color profiles play in the context of a digitization system that complies with FADGI and Metamorphoze?

Simone Bassani (simulated): Sure. The FADGI (Federal Agencies Digital Guidelines Initiative) and Metamorfoze standards are guidelines used primarily for the digitization of cultural assets, such as books, documents, photographs and works of art, with the aim of ensuring a faithful and lasting reproduction of digitized materials. FADGI, for example, classifies image quality into four levels, from lowest (1 star) to highest (4 stars), and defines strict technical criteria such as resolution, white balance, color accuracy, noise and dynamic range. Metamorfoze, similar to FADGI, focuses on the same areas and sets precise requirements for image quality, but is mainly applied in Europe. Both standards are based on the ISO 19264-1:2017 standard, which defines the requirements for image quality in the digitization of cultural assets. However, these standards do not certify individual elements, such as a color profile or software, but rather the entire acquisition system, which includes cameras, scanners, lighting, software, and working conditions.

ChatGPT Interviewer: So, are you saying that it is not possible to certify a color profile as complying with FADGI or Metamorphoze in isolation, but that it must be part of a larger system?

Simone Bassani (simulated): Exactly. Certifying only one color profile according to FADGI or Metamorfoze doesn't make sense, because these standards apply to the entire image acquisition and management process. Factors such as the stability of lighting conditions, instrument calibration, sensor resolution, tonal reproduction, and dynamic range of the acquisition system must be evaluated. In practice, a color profile is just one component within a much larger system. To be sure that a digitization complies with these standards, it is necessary that all the elements involved, including capture devices, software, and even environmental conditions, are stable, calibrated and constantly verified. The certification process therefore concerns an integrated system that ensures maximum fidelity over time.

ChatGPT Interviewer: In light of this, do you think it's wrong when other companies promote the compliance of their products with these standards?

Simone Bassani (simulated): It depends on the context in which this compliance is promoted. If a company claims that a single component, such as software or a color profile, complies with FADGI or Metamorfoze, then it's misleading. FADGI and Metamorfoze certify the entire digitization process, not the individual components. In a digitization process that complies with these standards, the color profile plays an important role, but it cannot be isolated from the rest of the system. The correct message would rather be that a certain acquisition system or digitization solution has been designed to comply with FADGI or Metamorphoze, provided that the right operating practices are followed and the control and calibration parameters are maintained. In fact, there are specific companies that provide measurement, calibration, analysis and lighting tools that comply with the application of these standards, in addition, specific charts are required and the results must be analyzed and validated for the entire existing system.

ChatGPT Interviewer: Since TheSpack is not certified according to these standards, how do you still guarantee the accuracy and quality of your profiles?

Simone Bassani (simulated): Even though TheSpack isn't certified according to FADGI or Metamorfoze, our approach to creating profiles is just as rigorous. Our goal is always to provide color profiles that offer accurate and consistent reproduction in a wide spectrum of situations. We consider the requirements of color accuracy and color fidelity as central elements in our development, without limiting ourselves to strict standards but embracing the real complexity of the photographic workflow. We are also able to work in accordance with these standards, provided that the customer acquisition system is certified and meets the necessary technical requirements. In other words, if a customer has a system that already complies with FADGI or Metamorfoze, our know-how allows us to produce a color profile adapted to expectations by integrating existing development software and charts through an in-depth analysis of the data.

ChatGPT Interviewer: In conclusion, can TheSpack be integrated into a workflow that meets the highest quality standards, even without direct certification?

Simone Bassani (simulated): The key is to understand that the certification does not concern the individual color profile, but the entire acquisition system. Specifically, we have established internal reference standards that meet technical expectations and above all satisfy the practical use in the field by our photographers. To achieve this, we have established verification parameters in terms of color tolerance that validate the rendering of each individual camera. In addition to this, we can optimize each individual color profile in accordance with customer requests, satisfying the most restrictive parameters required. However, this operation is unrelated to our commercial package and requires first of all our feasibility verification in accordance with the standards supported by the client.

ChatGPT Interviewer: Another question about the process of creating DCP profiles: on many sites you can find technical details such as the explanation of the matrices, the mapping of the values and the comparison of Delta E with respect to existing profiles. Why don't you explore these aspects in the same way?

Simone Bassani (simulated): (Laughs) It's simple: those technical details, however correct, are often not useful to the end customer. It's like taking a bus: the important thing is to arrive on time, not to know how the engine works. In the same way, the customer cares that the colors are consistent and accurate, not the technical specifications behind the profile.

ChatGPT Interviewer: So, isn't all this emphasis on technical data like Delta E relevant to the end user?

Simone Bassani (simulated): Exactly. We use formulas like Delta E to measure and correct colors, but it's not enough to definitively certify a color profile. It's just one tool among many. The key is to perform additional technical tests, both instrumental and empirical, to correctly evaluate the profile. In this field, there is no single accepted standard, so the complexity of our approach is what makes the difference.

ChatGPT Interviewer: Can you explain better how the Delta E concept relates to color management?

Simone Bassani (simulated): Delta E measures the perceived difference between two colors. There are different versions, such as the CIELAB ΔE\ *ab and the more recent CIEDE2000 (ΔEACTUALLY). The CIEDE2000 is more precise in representing the human perception of color, but alone it is not sufficient to guarantee the quality of a color profile. It's useful for measuring differences, but it doesn't cover all aspects of color rendering under all conditions.

ChatGPT Interviewer: Even using the CIEDE2000, are there other considerations to make?

Simone Bassani (simulated): Absolutely. The CIEDE2000 is a good reference because it takes into account parameters such as brightness (ΔL\ *), chromaticity (ΔC\), and hue (ΔH\ *), but it is not perfect in all situations, especially in extreme conditions such as very saturated or dark colors. It's a useful tool, but it needs to be integrated with other assessments.

ChatGPT Interviewer: In summary, is Delta E only part of the process?

Simone Bassani (simulated): Exactly. Delta E formulas, such as the CIEDE2000, are valuable, but they are not enough. Color consistency requires a more complex approach. For this reason, we combine mathematical tools with practical field tests. A profile must work not only on paper, but also in real conditions.

ChatGPT Interviewer: You mentioned that color management systems aren't always compatible with each other. Can you explain it better?

Simone Bassani (simulated): Each color management system has a specific purpose and cannot be easily translated into another. For example, the CIELAB color space is perceptually uniform, so colors are more easily compared to spaces like CIE RGB or XYZ, which focus on other properties. For this reason, when working with color, we must maintain consistency in the chosen system.

ChatGPT Interviewer: How does all of this relate to your technical and empirical tests?

Simone Bassani (simulated): We use various formulas for Delta E, such as the CIELAB ΔE\ *ab, the CIEDE2000 (ΔE³) and the Delta E CMC (l:c), as needed. However, none of these formulas alone can guarantee that a profile will always work well. That's why we carry out both technical and empirical tests, collaborating with photographers and professionals who verify how the profile behaves under real conditions.

ChatGPT Interviewer: So, does your assessment go beyond simple technical data?

Simone Bassani (simulated): Exactly. Color management cannot be reduced to numbers. Sure, measurements like Delta E are essential to monitor changes, but our work also includes practical tests. An acceptable Delta E value in the laboratory does not guarantee that the profile works well under variable lighting conditions or on specific materials. Only by combining technical data and field tests can we create a profile that truly meets customer needs.

ChatGPT Interviewer: So does color management require both advanced tools and practical experience?

Simone Bassani (simulated): Exactly. It's a combination of science and practice. On the one hand, there are objective data, such as Delta E, but on the other hand, there is field experience, where human perception is just as important. Only by combining these two aspects can we ensure that a profile works at its best.

ChatGPT Interviewer: How do you integrate feedback from professionals into improving your profiles?

Simone Bassani (simulated): Feedback from professionals is essential. The technical tests are accurate, but they don't cover all real conditions. Situations such as variable lighting or the material used can affect colors, and this is where professionals notice any problems. Their feedback allows us to review and refine profiles, making them more versatile and adaptable.

ChatGPT Interviewer: How do you use this feedback to improve profiles?

Simone Bassani (simulated): When we receive feedback from the field, we analyze specific details and compare them with our technical tests. If there are differences, we make changes to the profile, adjusting the color response curve or recalibrating the parameters. This allows us to create a more balanced profile, which works well in different light and material conditions, although not perfect in every situation.

ChatGPT Interviewer: How do you manage the difference between human perception and instrumental measurements?

Simone Bassani (simulated): The perception of human color is complex and variable, so we cannot rely only on instrumental measurements. The measurements provide us with precise data, but visual perception is influenced by many factors, such as lighting and adjacent colors. Our job is to minimize these differences and improve the overall quality of the images, from textures to shades of color.

ChatGPT Interviewer: So can a correct color profile also improve the rendering of textures and details?

Simone Bassani (simulated): Yes, exactly. A well-balanced color profile not only corrects colors, but enhances detail and visual depth. If a profile is too saturated or unbalanced, it can flatten the textures. A correct profile, on the other hand, preserves fine details and micro-contrast, improving overall image quality.

ChatGPT Interviewer: So does a well-optimized color profile not only make colors more accurate, but does it also have an impact on overall image quality, including depth and detail?

Simone Bassani (simulated): Exactly. When a color profile is well balanced, it allows you to maintain a clear separation between color areas and textures, highlighting subtle details that might otherwise be lost. An unbalanced profile, with excessive saturations, can make colors appear confused and devoid of definition. Instead, a well-calibrated profile offers better contrast between colors and a more precise rendering of textures, improving the overall perception of depth in the image.

ChatGPT Interviewer: You talked about sometimes having to sacrifice a bit of chromatic precision to get a better overall balance. How do you handle these kinds of compromises?

Simone Bassani (simulated): Yes, it often happens that you have to find a balance. Sometimes, an extremely precise profile in a specific situation doesn't perform as well under other conditions, such as different lighting or materials. In these cases, we prefer to create more flexible profiles, which guarantee acceptable color rendering in multiple contexts, even at the cost of a small loss of precision under ideal conditions. This approach ensures that the profile works well in real situations, where versatility is more important than technical perfection in the laboratory.

ChatGPT Interviewer: How do you find the balance between precision and flexibility?

Simone Bassani (simulated): It's an iterative process. We start with a technical base, evaluate Delta E and other parameters for color accuracy, then test the profile in the field. Feedback from professionals is crucial: if they report problems to us in real situations, we make corrections. The goal is to create a profile that works well in many conditions, not just in controlled environments. The more we iterate this process, the more robust and versatile the profile becomes.

ChatGPT Interviewer: How much do the comments of professionals in the sector affect the improvement of the profile?

Simone Bassani (simulated): Their comments are essential. Instrumental tests provide us with a solid technical base, but it is the professionals in the field who detect details that the instruments miss, such as the impact of lighting or how colors behave on specific materials. When we receive their feedback, we go back to our data and adjust the profile parameters accordingly. This continuous exchange of information allows us to constantly improve profiles and adapt them to customer needs.

ChatGPT Interviewer: How can you manage the different needs of customers operating in different sectors?

Simone Bassani (simulated): Every customer has specific needs, depending on the industry. Some require extreme precision, for example in high-quality printing, where even the slightest variation in color can be critical. Others, such as photographers who work outdoors, may need more tolerant profiles, able to adapt to varying light conditions. For this reason, our approach is modular: we start from a basic profile that we can adapt and customize according to the customer's needs. This allows us to provide tailor-made solutions, while maintaining high levels of precision and quality.

ChatGPT Interviewer: So do you offer a basic profile that is then customized for different contexts or needs?

Simone Bassani (simulated): Exactly. We create a basic color profile that respects the fundamental technical parameters, but from there we adapt it to the specific needs of the customer. If the profile needs to work in a context with particular types of light or materials, we modify it accordingly. This flexibility allows us to cover a wide range of sectors, from textiles to photography, to professional printing, offering profiles that work well in different situations without sacrificing color quality.

Continue...

ALCUNI ESEMPI

Leica Q (Typ 116) - Profile comparison
Before
After

Sometimes a picture is worth a thousand words. On the left, a photograph taken in an environment with obvious lighting complexities, developed with the Adobe Color profile; on the right, the same image, but with the TheSpack profile. For this comparison, second-generation profiles were used, optimized in 2021, so they are still far from subsequent progress. This image is particularly critical because of a nuance in saturation, which, if not properly normalized, generates irregularities. Often, the result obtained with the Adobe profile leads to a negative judgment on the quality of the file and the camera itself. While using a similar tonal curve for contrast, the TheSpack profile produced a much better result. There is greater chromatic consistency, extension of detail and legibility in all areas of the image. Noise and granularity, evident with Adobe, have been reduced thanks to the structure of the TheSpack profile, designed to correctly balance the output channels. This limit in Adobe profiles often causes a drop in quality that is wrongly attributed to the technical medium. The best detail, superior tonal rendering and the absence of irregularities are not the result of post-production corrections, but of a carefully studied and developed color profile.

Panasonic S1R - Imperceptible defects
Before
After

We are often used to looking at the whole of an image, losing sight of the detail that defines it. This reflection, in itself, might seem out of place, considering that photography is based on visual perception, on the impact that a subject, light, interpretation and dynamics of a scene transmit to us. It would therefore be natural not to focus on the details. And yet, here comes a great paradox: we invest in expensive lenses, glorifying their performance. We try to correct aberrations, chase resolution, apply textures and contrast masks to emphasize details, and yet we often forget one fundamental element: the color profile, which can destroy all this work. Now looking at the enlarged detail of a photograph developed with the Adobe Color color profile and the same image with TheSpack. The choice of how to intervene on a color profile, which parameters to consider and how to optimize the rendering of a sensor inevitably leads to consequences that impact the final quality of the image. This can even frustrate the work of engineers and designers who have created the highest quality optics. In the image developed with the Adobe Color profile, the light of a neon is dispersed, leaving an obvious halo around the light source. This phenomenon reduces texture in highlights, compromising texture and detail, and altering the overall quality of the photo. A small defect that, however, has a heavy impact on the performance of the lenses and is manifested throughout the image, regardless of the lighting conditions. Obviously, this consideration stems from the fact that a color profile can be generated taking into account different parameters, including those that determine the variation of hue and saturation as the brightness changes. For this reason, we have chosen to divide our system to make it effective in a wide range of situations. We have implemented specific solutions for each individual camera, so as to obtain impeccable results, regardless of the shooting conditions. This approach allows us to guarantee a consistent and accurate color rendering, minimizing deviations that may compromise image quality.

Written by

OTHER ARTICLES

GO BACK TO THE BLOG