Changan Chen's repositories
awesome-embodied-vision
Reading list for research topics in embodied vision
RelationalGraphLearning
[IROS20] Relational graph learning for crowd navigation
socialforce
Numpy implementation of the Social Force model.
linux_config
Configure bash and vim environment in one line
action2sound
Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos
CS380D-proj2
Implementation of two-phase commit protocol for course CS380D
ActionRecognition-1
Simple action recognition model for starters
MultiagentRGL
Relational Graph Learning for Multiagent Navigation
awesome-vln
A curated list of research papers in Vision-Language Navigation (VLN)
learning-to-learn-sparsity
Use a meta-network to learn the importance and correlation of neural network weights
Diff-Foley
Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models
epic-kitchens-100-narrator
Video narrator written in Python/GTK using vlc-lib
habitat-api
A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators.
habitat-challenge
Code for the habitat challenge
habitat-sim
A flexible, high-performance 3D simulator for Embodied AI research.
hifigan-denoiser
HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
ImageQuilting
The goal of this assignment is to implement the image quilting algorithm for texture synthesis and transfer, described in this SIGGRAPH 2001 paper by Efros and Freeman. Texture synthesis is the creation of a larger texture image from a small sample. Texture transfer is giving an object the appearance of having the same texture as a sample while preserving its basic shape (see the face on toast image above). For texture synthesis, the main idea is to sample patches and lay them down in overlapping patterns, such that the overlapping regions are similar. The overlapping regions may not match exactly, which will result in noticeable edges. To fix this, you will compute a path along pixels with similar intensities through the overlapping region and use it to select which overlapping patch from which to draw each pixel. Texture transfer is achieved by encouraging sampled patches to have similar appearance to a given target image, as well as matching overlapping regions of already sampled patches. In this project, you will apply important techniques such as template matching, finding seams, and masking. These techniques are also useful for image stitching, image completion, image retargeting, and blending.
JSON2HTML-parser
Convert Json files to formatted and colorized HTML files
my_shell-1
A mini yet useful shell
react-eggjs-starter-kit
A basic start kit with React as frontend and Eggjs as backend, along with mySQL
SemanticCorrectnessScore
Detector-based score for measuring semantic correctness of images
SpecVQGAN
Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)
speechbrain
A PyTorch-based Speech Toolkit