Xiaoke Huang's repositories
segment-caption-anything
[CVPR 24] The repository provides code for running inference and training for "Segment and Caption Anything" (SCA) , links for downloading the trained model checkpoints, and example notebooks / gradio demo that show how to use the model.
OrdinalCLIP
[NeurIPS 2022] OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression
benchmark-referring-vllm
We benchmark VLLM for referring image captioning. From paper "Segment and Caption Anything"
Promptable-GRiT
Promptable GRiT: support inference with both automatic proposal generation and custom point/box prompts.
nerf.mindspore
Neural radiance field with mindspore. w/ checkpoint, re-imp. performance, and ipynb to play around.
MakeItTalk
add docker
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
240416-research-contributions
(Custom) Try UNETR, MONAI research-contributions
azfuse
(comp. w/ oldest azure-storage-blob) A lightweight blobfuse-like python tool with the data transfer through azcopy
azure-storage-python
(change to old version) Microsoft Azure Storage Library for Python
cli-dictionary
(add phonetic and syn ant) Dictionary for command line.
EasyMocap
(fix path, use my SCHP) Make human motion capture easier.
embeddings
Fast, DB Backed pretrained word embeddings for natural language processing.
nerf
(update llff) My re-implementation of NeRF.
neuralbody
(add visualization, for ema video) Code for "Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans" CVPR 2021 best paper candidate
segment-anything
(visualization mode in amg) The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Self-Correction-Human-Parsing
(fix the code, for EasyMoCap) An out-of-box human parsing representation extractor.
stable-diffusion-webui-docker
(adapt the proxy) Easy Docker setup for Stable Diffusion with user-friendly UI
surface-aligned-nerf
for ema. fix comparison on h36m
tava
(minor update, for ema) Code for the paper "TAVA Template-free Animatable Volumetric Actors".
vdtk
(For "Segment and Caption Anything ", use "dev" branch) Visual Description Dataset Analysis Toolkit