Review of Dense Surface Reconstruction

less than 1 minute read

Published:

Presentation slides for in-depth tech talk on dense 3D point cloud reconstruction from 2D images.

Description:

This PDF presentation is a talk I have given at several venues that provides an overview of the topic of dense 3D surface reconstruction 2D images. It includes 30 literature references on subtopics of the overview including many landmark papers in computer vision. The presentation covers both theory and implementation aspects of 3D surface reconstruction including discussions on camera calibration, disparity estimation, and 3D point cloud generation.

Teaser Image:

Teaser Image

You May Also Enjoy

Literature Notes: On-Device LLM Training

11 minute read

Published:

Collection of notes from papers on the topic of training LLMs (and where possible, ML models in general) on edge devices. Most software libraries and literature aimed at on device operation are aimed at efficient inference. Training on device is a less-developed area. Training on device is useful in applications where a model must be fine tuned for individual use cases.

Python Bindings for Performance Optimization: A Zero to One Guide

8 minute read

Published:

This article describes techniques to accelerate a Python codebase by exposing parallelized C++ functions using PyBind. It then analyzes the results of the optimization in which parallelizing one 40-line function in a 700-line program yielded up to a 3X end-to-end speedup.

Segmentation For Holographic Images

2 minute read

Published:

Patent I authored while working at Microsoft. Describes an image segmentation technique for producing photorealistic human holograms.

Technical Interview Materials

less than 1 minute read

Published:

My most popular GitHub project: C++ and Python solutions to Cracking the Coding Interview.