Ash's repositories
Blender-ControlNet
Using ControlNet right in Blender.
neural_congealing
Official implementation of the paper "Neural Congealing: Aligning Images to a Joint Semantic Atlas"
tinyengine
[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory
UniversalHumanoidControl
Official Implementation of the Universal Humanoid Controller
Grounding-Language-Models-to-Images-for-Multimodal-Generation
🧀 Code and models for the paper "Grounding Language Models to Images for Multimodal Generation".
An-Open-Bilingual-Pre-Trained-Model-ICLR-2023-
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
CutLER
Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation"
EmbodiedPose
Official implementation of NeurIPS 2022 paper: "Embodied Scene-aware Human Pose Estimation".
ICON
ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)
Malt
Render framework for NPR.
Meshroom
3D Reconstruction Software
metaseq
Repo for external large-scale work
mm-cot
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
MTR
MTR: Motion Transformer with Global Intention Localization and Local Movement Refinement, NeurIPS 2022.
nadir
Nadir is a library of bleeding-edge optimisers built for speed and functionality in PyTorch for researchers 💙
rust
Empowering everyone to build reliable and efficient software.
Scene-Diffuser
Official implementation of CVPR23 paper "Diffusion-based Generation, Optimization, and Planning in 3D Scenes"
TalkSHOW
This is the official repository for TalkSHOW: Generating Holistic 3D Human Motion from Speech [CVPR2023].
uform
Multi-Modal Inference Library For Semantic Search Applications and Mid-Fusion Vision-Language Transformers
whisper
Robust Speech Recognition via Large-Scale Weak Supervision
ZoeDepth
Metric depth estimation from a single image