Explore @aim-uofa Open Source projects

Adelaide Intelligent Machines (AIM) Group (@aim-uofa)

aim-uofa

Stars
6,722
Global Org. Rank 3,468 (Top 2 %)
Registered almost 5 years ago
Most used languages

Python
90.5 %

JavaScript
4.8 %

Jupyter Notebook
4.8 %
Location 🇨🇳 China
Country Total Rank 1,037
Country Ranking

Python
124

Jupyter Notebook
1,227

AdelaiDet

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

AdelaiDepth

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.

Matcher

[ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

MovieDreamer

StyleDrop-PyTorch

This is an unofficial PyTorch implementation of StyleDrop: Text-to-Image Generation in Any Style.

Poseur

[ECCV 2022] The official repo for the paper "Poseur: Direct Human Pose Regression with Transformers".

AutoStory

GenPercept

GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

DyCo3D

FrozenRecon

[ICCV2023] 🧊FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models

SegPrompt

Official Implementation of ICCV 2023 Paper - SegPrompt: Boosting Open-World Segmentation via Category-level Prompt Learning

FreeCustom

[CVPR 2024] Official PyTorch implementation of FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

OIR

[ICLR 2024] Official PyTorch/Diffusers implementation of "Object-aware Inversion and Reassembly for Image Editing"

RGM

GeoBench

A toolbox for benchmarking SOTA discriminative and generative geometry estimation models.

GenDeF

DiverGen

DiverGen (CVPR 2024) & BSGAL (ICML 2024)

LoRAPrune

FreeCompose

Jupyter Notebook

SINE

[NeurIPS'24] A Simple Image Segmentation Framework via In-Context Examples

VFN

[ICLR 2024 Spotlight] The official repo for the paper "De novo Protein Design using Geometric Vector Field Networks".

partially-labelled

Learning to segment multi-organ and tumorsfrom multiple partially labeled datasets

FADiff

[ICML 2024] Floating Anchor Diffusion Model for Multi-motif Scaffolding

Depth3D

VLModel

Repo of HawkLlama.

STORY

OIR-Diffusion