AI-900 Practice Question: Describe features of computer vision workloads on Azure
What is 'neural radiance field' (NeRF) technology and how does it relate to Azure AI Vision capabilities?
⚠ Common exam trap
Candidates often confuse NeRF with traditional 3D rendering techniques (like shaders or game engines) or unrelated networking concepts, rather than recognizing it as a neural 3D scene representation method for novel view synthesis.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
A method for learning 3D scene representations from multiple 2D photographs to enable novel view synthesis
Neural Radiance Fields (NeRF) use a neural network to learn a continuous 5D representation of a scene from a sparse set of 2D photographs, enabling the synthesis of novel views from arbitrary camera angles. This relates to Azure AI Vision capabilities because Azure's Computer Vision services can be integrated with NeRF-based models for advanced 3D reconstruction and volumetric rendering tasks, such as generating immersive 3D assets from 2D images in mixed reality or digital twin scenarios.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A technique for compressing neural network weights using magnetic fields
Why it's wrong here
This option is nonsensical in context: NeRF does not compress neural network weights, and magnetic fields have no involvement in its 3D reconstruction process. Model compression techniques (e.g., pruning, quantization) reduce parameter size, whereas NeRF instead learns a scene representation from images. The explanation is wrong because NeRF is a 3D scene learning method, not a weight-compression scheme.
- ✓
A method for learning 3D scene representations from multiple 2D photographs to enable novel view synthesis
Why this is correct
Neural Radiance Fields (NeRF) represent a scene as a continuous volumetric function, mapping a 3D position and 2D viewing direction to an emitted color and volume density. This function is encoded in a multilayer perceptron trained on multiple posed 2D photographs, and novel viewpoints are generated by ray-marching through the volume and integrating color/density along each ray. The result is photorealistic synthesis of perspectives never captured by the original camera.
- ✗
A networking technology that transmits images with zero packet loss
Why it's wrong here
This confuses a computer vision technique with data networking. Reliable image delivery with zero packet loss is a transport-layer concern, typically addressed by protocols like TCP that retransmit lost packets or by application-level error correction. NeRF operates on already-received 2D images to reconstruct a 3D scene; it has no role in network transmission, packet handling, or loss recovery.
- ✗
A type of GPU shader program used for real-time 3D rendering in games
Why it's wrong here
GPU shader programs are hand-coded or compiled stages in the traditional rasterization pipeline (vertex, fragment, etc.) that run on the GPU to color pixels in real time. NeRF is a learned implicit 3D representation that requires neural network inference and volumetric ray-marching, which is computationally heavier and not part of the fixed-function real-time graphics pipeline. While NeRF outputs can be rendered, the method itself is a machine learning model, not a shader.
Go deeper
Related to this question
Learn chapter
Deep Learning and Neural Networks
Key term
Neural network
A neural network is a computing system modeled loosely on the human brain that learns to recognize patterns from data without being explicitly programmed for every rule.
Key term
Computer vision
Computer vision is a field of artificial intelligence that enables computers to interpret and make decisions based on visual data from the world, such as images and videos.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.