Reflections on My Literature Review

-

Over the past few weeks, I have been researching understand how artificial intelligence (AI) can be integrated into 3D software—specifically Houdini and Blender—to enhance visual effects (VFX) workflows. This process wasn’t just about gathering sources or ticking boxes for an assignment; it was a deep dive into the evolving intersection of AI, machine learning operations (MLOps), natural language processing (NLP), and procedural generation. Here’s a candid reflection on what I learned, the problems I faced, and the steps I plan to take as I continue refining my work.

Discovering the Building Blocks

My literature review started by focusing on key foundational ideas:

  • MLOps as the Backbone: I found a GitHub repository by Bismuth Consultancy BV (n.d.) that introduced me to MLOps—a critical concept that bridges traditional DevOps with the specific needs of AI workflows. This resource gave me a practical understanding of how AI systems are managed, from data versioning to model retraining.

  • The Role of NLP: Collobert et al. (2011) provided a comprehensive look into NLP, demonstrating how layered neural architectures can perform complex tasks like part-of-speech tagging and semantic role labeling. Although their work centers on text processing, it sparked an idea: what if a similar approach could be used to manage 3D asset generation through an API-based setup in Houdini?

  • Identifying Gaps and Opportunities: Meanwhile, Matsui and Goya (2022) pushed me to think about the gaps between automation and machine learning within MLOps. Their insights helped me see that while many topics connect broadly to AI, the specifics of integrating these concepts into 3D workflows require further exploration.

Structuring My Review

To bring clarity to my research, I divided my review into four parts:

  1. MLOps and AI Workflow: This section discusses how DevOps principles have evolved into MLOps, and how these practices can be adapted to streamline AI operations within creative tasks. I even explored how Houdini’s Python interface can serve as a bridge for integrating these concepts.

  2. NLP: Here, I delved into the work of Collobert et al. (2011) to understand foundational NLP techniques. The idea of using text-based commands to generate or modify 3D assets emerged as particularly exciting, suggesting a future where creative processes are as intuitive as typing a command.

  3. Test MLOps in Houdini and Blender: Drawing on frameworks from Bayram and Ahmed (2024), Paleyes et al. (2022), and Bommasani et al. (2021), I examined ethical considerations and risk management strategies in deploying AI. This section was a reminder that technology is only as good as the responsibility with which it’s used.

  4. Procedural and Generative Techniques in 3D Software: This part compares traditional procedural generation—as described by Shaker et al. (2016)—with cutting-edge innovations like the text-to-NeRF method proposed by Zhang et al. (2023). It paints a picture of a continuum, where established methods are stepping stones to future innovations.

Lessons Learned and Reflections

During my research, I encountered several challenges. SO, while I researched some topics, my gap was narrow. I wasn’t able to track down a lot that directly connected to my specific focus. However, this struggle wasn’t wasted—it helped me understand the broader landscape of foundational AI and the technologies surrounding it. I learned that even if a source doesn’t directly address my narrow topic, it still plays a crucial role in building a comprehensive understanding of the field.

This process taught me two vital lessons:

  1. Broaden Your Horizons: While it’s important to have a focused research question, exploring related fields like general AI principles, MLOps, and NLP can provide invaluable context that enriches your work.

  2. Commit to Continuous Improvement: I recognize that I still need to work a lot harder to fully grasp these complex concepts and integrate them seamlessly into my literature review. This is just the beginning, and each step of the process has motivated me to delve deeper and refine my understanding further.

Looking Ahead

Moving forward, I plan to:

  • Expand my research by seeking out additional interdisciplinary sources that connect AI’s theoretical foundations with its practical applications in 3D software.
  • Enhance the synthesis in my review, linking disparate sources to build a more cohesive narrative that underscores the transformative potential of integrating AI into creative workflows.
  • Refine my approach by addressing ethical considerations more robustly and clearly outlining the future implications of these technologies for both users and creators.

In essence, this literature review has not only provided me with a theoretical backbone but has also ignited a passion to explore how emerging AI technologies can revolutionize the creative process. While there is still much to learn, the journey so far has been both humbling and inspiring—and I’m excited to continue pushing the boundaries of what’s possible.

Comments

Post a Comment

Popular posts from this blog

Present Best Way to Install MLOPs in Houdini

-
Image
I had an issue while installing MLOPs just following the tutorial, and to solve the problems, I went to different communities but got no solution, in the end, Bismuth's discord community, I got an answer from @.jaydrake who gave me the best steps for the current time to make MLOPs work. Thank you for saving my project. Below are the steps that currently work for setting up MLOPs, which are needed to use Open AI API, with the help of one of the users in the BV's discord server @.jaydrake. Setting up and installing MLOPs: 1. Checking your Python version with Houdini's Python Interpreter by going to the main options bar at the top where Windows -> Python Shell . 2. The choice of Python Interpreter depends upon the user if they will use an external Python environment or hython, which is Python in Houdini. 3. Then go to https://github.com/Bismuth-Consultancy-BV/MLOPs , and install GitHub Desktop, which is the best way to clone the repository inside your computers. This metho...
Read more

Color Ramp Generator

-
Image
I chose one of the most effortless node-based AI approaches for my first experiment: color ramp. It's similar to a gradient bar you see in Adobe Creative Suite, which in Houdini can be used to create a gradient effect over any line or shape made in Houdini; it's easy as it's a node that can be manipulated by parameter. By connecting Open AI API, I can make it a prompt-based approach without any problem where user text base input will be interpreted via a Python code and will give results to change the color ramps.  Using Houdini for this project gives me an advantage as it allows me to interact with the nodes already in the Houdini workspace using Python, also known as Python (Houdini + Python).  Color Ramp AI Node 1. Create a Python node named " color_ramp_GPT ," adding the below code in the content area.  from openai import OpenAI import hou import ast node = hou.pwd() client = OpenAI() def get_completion(user_prompt, system_message):     try:     ...
Read more

Researching topics for My Thesis (Master's Edition)

-
Image
Below are some of the ideas that popped up in my mind while thinking about what technology I can work on, which will help me learn and also contribute to the field of Digital Media. 1. Topics: Streamlining steps to procedurally generate landscapes in Houdini and Unreal Engine by testing tools with the help of AI! This will help artists work on the parameters to change the landscape, and AI can reduce time by building up the structure and connections required to build that landscape. Whenever I work on any project involving big maps, it makes me feel overwhelmed by how much time it takes to build something from scratch, and procedural generation is one of the solutions that made me feel how much we can improve it just by adding AI. If I could find a tool, the pipeline for developing landscapes would become more streamlined than ever for environmental designers. PCG is research where they use GAN to make landscapes via Height maps. Need to Experiment with AI and work on the concepts to ...
Read more