Saral Shiksha Yojna
Courses/Computer Vision

Computer Vision

CSE471
Prof. Makarand Tapaswi + Prof. Charu Sharma•Spring 2025-26•4 credits
Revision Notes/Unit 2 — Dense Prediction: Segmentation + Depth

Unit 2 — Dense Prediction: Segmentation + Depth

From sparse boxes to per-pixel labels. FCN, U-Net, dilated convolutions, Mask R-CNN and RoI Align for segmentation; MiDaS and scale-invariant losses for depth.

Dense Prediction — Segmentation & Monocular Depth

15 min

Detection labels regions; dense prediction labels pixels. The architectural challenge is restoring spatial resolution lost during downsampling — usually with transposed convolutions, skip connections, or dilated convolutions.