Skip to content
tezvyn:

Computer Vision

Image/video models, diffusion, OCR, multimodal

135 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.

Interview questions in Computer Vision, page 2

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

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

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.

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.

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.

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.

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.

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.

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.

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.

advanced1 min read

Stereo rectification math and its artifacts

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

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.

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

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.

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.

intermediate1 min read

ResNet residual blocks and the degradation problem

A residual block learns F(x) and adds the identity input x, so layers fit a residual; this eases gradient flow and solves the degradation problem.

intermediate1 min read

Receptive fields in convolutional networks

Receptive field is the input region affecting a neuron; it grows with depth, larger kernels, and stride. It matters for capturing context in detection and segmentation.

intermediate1 min read

Uses of the 1x1 convolution

A 1x1 conv is a per-pixel linear combination across channels; it reshapes channel depth cheaply and adds nonlinearity. Uses: dimensionality reduction in bottlenecks and channel mixing.

advanced1 min read

Adapting a classification CNN for segmentation

Replace the dense head with conv layers, upsample via transposed convolutions, and fuse encoder skip connections to recover spatial detail lost to downsampling.

advanced2 min read

Depthwise separable convolution cost savings

Separable conv splits standard conv into per-channel spatial filtering plus a 1x1 pointwise mix, cutting cost by roughly 1/N plus 1/k².

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