Skip to content
tezvyn:

Computer Vision

Image/video models, diffusion, OCR, multimodal

301 bites

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

Everything in Computer Vision, page 6

intermediate1 min read

Regularization techniques for an overfitting CNN

Data augmentation expands the effective dataset, dropout prevents co-adaptation, weight decay penalizes large weights, plus early stopping and batchnorm.

easy1 min read

Why CNNs need nonlinear activations like ReLU

ReLU introduces nonlinearity letting stacked layers model complex functions; without it any stack collapses to a single linear map.

easy1 min read

Max pooling versus strided convolution

Pooling downsamples and adds small translation invariance with no parameters; strided conv learns its downsampling but adds parameters.

easy1 min read

How a convolutional layer works

Learnable kernels slide over the input computing dot products, with stride controlling step size and padding controlling output size.

advanced1 min read

Stereo rectification math and its artifacts

Rectification warps both images by homographies so epipolar lines become horizontal and aligned.

intermediate1 min read

The PnP problem in Structure from Motion

PnP recovers a camera's pose from known 3D points and their 2D projections; it registers new frames against the existing point cloud in SfM.

intermediate2 min read

Incremental Structure from Motion pipeline

Detect and match features, estimate two-view geometry, triangulate, then incrementally add images with PnP and refine via bundle adjustment.

intermediate2 min read

Fundamental matrix versus essential matrix

Both relate corresponding points across two views via the epipolar constraint; the fundamental matrix works in pixel coordinates, the essential matrix in calibrated coordinates and encodes relative pose.

easy2 min read

Disparity and depth in stereo vision

Disparity is the horizontal shift of a point between left and right images; depth is inversely proportional to disparity given baseline and focal length.

easy2 min read

Epipolar constraint for correspondence search

The match for p1 must lie on its epipolar line in the second image, reducing a 2D search to 1D; the relation is encoded by the fundamental matrix.

advanced2 min read

Feature choice for real-time mobile SLAM

Pick ORB for fast FAST keypoints and cheap binary descriptors matched by Hamming distance; accept reduced robustness versus SIFT for real-time, low-power operation.

advanced2 min read

CNN features for image retrieval

Pass the image through a pretrained CNN and read activations from a late layer as a descriptor; deeper layers encode semantics, earlier layers encode texture.

intermediate2 min read

Bag of Visual Words model

Cluster many local descriptors (e.g. k-means) into visual words; assign each image's features to words; represent the image as a histogram of word counts for a classifier.

intermediate2 min read

Descriptor matching and Lowe's ratio test

Match by nearest-neighbor descriptor distance; Lowe's ratio test keeps a match only if the best is clearly better than the second-best, rejecting ambiguous ones.

intermediate2 min read

SIFT versus SURF versus ORB

SIFT is most accurate but slow with float descriptors; SURF approximates SIFT for speed; ORB is fast, binary, and free, ideal for real-time and embedded.

intermediate2 min read

SIFT scale and rotation invariance

Scale-space extrema via difference-of-Gaussians give scale invariance; a dominant gradient orientation gives rotation invariance; the descriptor is a normalized gradient histogram.

easy2 min read

Image gradients, Sobel, and Canny

The gradient measures local intensity change in x and y; Sobel approximates it via convolution kernels; Canny uses gradient magnitude and direction plus non-max suppression and hysteresis.

easy2 min read

Harris corner detector and corner stability

Harris finds points where intensity changes strongly in all directions using the structure tensor of gradients; corners are well localized in two directions, unlike edges.

advanced2 min read

Image rotation: forward versus inverse mapping

Forward mapping sends source pixels to non-integer destinations, leaving holes and overlaps; inverse mapping iterates over output pixels, finds the source location, and interpolates.

intermediate2 min read

Removing salt-and-pepper noise

Use a median filter; it replaces a pixel with the neighborhood median so extreme outliers are discarded.

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