Daniel Haehn's Projects
Content pipeline tools for optimizing glTF assets. :globe_with_meridians:
Python interface to OpenJPEG library for reading and writing JPEG 2000 images.
A JavaScript implementation for reading the HDF5 file format.
It's a presentation framework based on the power of CSS3 transforms and transitions in modern browsers and inspired by the idea behind prezi.com.
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
We designed an instance-based compositional relation network (I-cRN) for machine graphical perception tasks by aligning with the actual human perception procedure.
Real Time Collision Avoidance Deep Learning Image Processing Alert System
Image-and-Spatial Transformer Networks
A jQuery plugin to build a website on the infinite canvas
2nd place solution for SIIM-OSIC Melanoma Classification
Inference code for LLaMA models
Magic Copy is a Chrome extension that uses Meta's Segment Anything Model to extract a foreground object from an image and copy it to the clipboard.
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Convolutional Neural Network for 3D meshes in PyTorch
Morphological snakes for image segmentation and tracking
Jetson Nano experiments.
WebGL-based viewer for volumetric data
Workflows and interfaces for neuroimaging packages
Web-based Electrode Visualization
Rendering one triangle, the WebGL/WebGPU way