Computer Vision

Image/video models, diffusion, OCR, multimodal

72 bites

Showing Interview + Intermediate

Test yourself: Top 30 intermediate Computer Vision interview questions →Multiple choice, with the correct answer and why it is correct on every question. Free, no sign-in.

Intermediate interview questions in Computer Vision, page 4

intermediate2 min read

Single vs multi-image super-resolution

SISR hallucinates detail from one image, multi-image fuses sub-pixel shifts; pixel losses blur, perceptual or GAN losses add realism.

intermediate2 min read

Triangulating 3D points from two views

Back-project each 2D point into a ray, intersect rays from both cameras using known poses, solve via DLT and refine by minimizing reprojection error.

intermediate2 min read

The role of anchor boxes in detectors

Anchors are reference boxes of set scales and ratios; the model regresses offsets, framing detection as classification plus refinement; downsides are tuning, imbalance.

intermediate2 min read

Why averaging shots reduces image noise

Random noise averages out while signal stays, so SNR rises with the square root of frame count; limits include motion and fixed-pattern noise.

intermediate2 min read

PTQ versus QAT for model quantization

PTQ quantizes a trained model with calibration data, fast but may lose accuracy; QAT simulates quantization in training so weights adapt.

intermediate1 min read

Homography vs fundamental matrix degeneracy

Homography fits planar scenes or pure rotation; fitting a fundamental matrix there is degenerate because points lack depth variation.

intermediate1 min read

How is IoU computed and why prefer mIoU?

IoU is intersection over union of predicted and true pixels; mIoU averages per class; pixel accuracy is dominated by background.

intermediate1 min read

Loss functions for imbalanced medical segmentation

Cross-entropy is swamped by background; Dice optimizes overlap directly; Focal down-weights easy pixels.

intermediate1 min read

Design real-time multi-object tracking for AV

Fast detector, Kalman motion model, Hungarian association on IoU plus appearance, track lifecycle for occlusions.

intermediate1 min read

Filter-based vs optimization-based SLAM

EKF folds past poses into one Gaussian; optimization keeps a sparse graph and re-linearizes; the latter wins on accuracy and loop closure.

intermediate2 min read

What does N-way K-shot classification mean?

N is classes per episode, K is labeled examples per class in the support set, prediction is on a separate query set.

intermediate1 min read

Design an active learning loop for detection

Seed-train, score the pool by uncertainty plus diversity, batch to annotators, retrain, repeat.

We are hiring for this. Every open role lists the topics its interview covers, so you can prepare for the real thing rather than guessing.

See open roles