VinAI Research

All

68 repositories

DiMSUM
Public
DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation (NeurIPS 2024)
architecture transformer image-generation diffusion-models flow-matching mamba-state-space-models
Python
•
GNU Affero General Public License v3.0
•0•16•1•0•Updated Dec 23, 2024Dec 23, 2024
SwiftBrush
Public
SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation (CVPR 2024)
Python
•
Other
•7•50•1•0•Updated Dec 9, 2024Dec 9, 2024
DiverseDream
Public
DiverseDream: A Technique to Generate Diverse 3D Objects from the Same Text Prompt (ECCV '24)
computer-vision nerf diffusion-models text-to-3d eccv2024
Python
•
GNU Affero General Public License v3.0
•0•7•0•0•Updated Dec 2, 2024Dec 2, 2024
HPR
Public
Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective (EMNLP 2024)
large-language-models generative-ai activation-editing
Python
•
GNU Affero General Public License v3.0
•0•4•0•0•Updated Nov 22, 2024Nov 22, 2024
CREPS
Public
Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesis (CVPR 2023)
generative-adversarial-network scale-invariance implicit-neural-representation stylegan3
Python
•
GNU Affero General Public License v3.0
•1•31•0•0•Updated Nov 17, 2024Nov 17, 2024
WhoQA
Public
Who's Who: Large Language Models Meet Knowledge Conflicts in Practice (EMNLP 2024 Findings)
1•6•0•0•Updated Nov 13, 2024Nov 13, 2024
PhoWhisper
Public
PhoWhisper: Automatic Speech Recognition for Vietnamese (2024)
BSD 3-Clause "New" or "Revised" License
•10•121•6•0•Updated Nov 12, 2024Nov 12, 2024
PhoGPT
Public
PhoGPT: Generative Pre-training for Vietnamese (2023)
vietnamese gpt vietnamese-nlp instruction-following llm generative-pre-trained-transformer phogpt
Python
•
BSD 3-Clause "New" or "Revised" License
•65•765•2•0•Updated Nov 12, 2024Nov 12, 2024
PhoNLP
Public
PhoNLP: A BERT-based multi-task learning model for part-of-speech tagging, named entity recognition and dependency parsing (NAACL 2021)
vietnamese-nlp multi-task-learning named-entity-recognition ner language-model pos-tagging dependency-parsing
Python
•
BSD 3-Clause "New" or "Revised" License
•17•138•0•0•Updated Nov 12, 2024Nov 12, 2024
blur-kernel-space-exploring
Public
Exploring Image Deblurring via Blur Kernel Space (CVPR'21)
python computer-vision deep-learning pytorch deblurring
Python
•
BSD 3-Clause "New" or "Revised" License
•35•151•14•0•Updated Nov 12, 2024Nov 12, 2024
CPM
Public
💄 Lipstick ain't enough: Beyond Color-Matching for In-the-Wild Makeup Transfer (CVPR 2021)
color computer-vision gan cvpr color-matching cyclegan pattern-detection color-transfer makeup face-manipulation
Python
•
BSD 3-Clause "New" or "Revised" License
•60•382•2•0•Updated Nov 12, 2024Nov 12, 2024
LeMul
Public
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images (ICCV 2021)
computer-vision deep-learning python3 pytorch unsupervised-learning 3d-reconstruction 3d-graphics iccv 3d-objects anaconda3
Python
•
BSD 3-Clause "New" or "Revised" License
•4•50•1•0•Updated Nov 12, 2024Nov 12, 2024
3D-UCaps
Public
3D-UCaps: 3D Capsules Unet for Volumetric Image Segmentation (MICCAI 2021)
unet hippocampus cardiac-segmentation capsnet capsule-network luna16 medical-image-segmentation iseg-challenge segcaps
Python
•
BSD 3-Clause "New" or "Revised" License
•14•69•8•0•Updated Nov 12, 2024Nov 12, 2024
PointSWD
Public
Point-set Distances for Learning Representations of 3D Point Clouds (ICCV 2021)
Python
•
BSD 3-Clause "New" or "Revised" License
•2•11•1•0•Updated Nov 12, 2024Nov 12, 2024
Point-Unet
Public
Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation (MICCAI 2021)
point-cloud-segmentation 3d-medical-imaging-segmentation
Python
•
BSD 3-Clause "New" or "Revised" License
•6•34•1•0•Updated Nov 12, 2024Nov 12, 2024
iFS-RCNN
Public
iFS-RCNN: An Incremental Few-shot Instance Segmenter (CVPR 2022)
Python
•
BSD 3-Clause "New" or "Revised" License
•4•13•4•0•Updated Nov 12, 2024Nov 12, 2024
HyperInverter
Public
HyperInverter: Improving StyleGAN Inversion via Hypernetwork (CVPR 2022)
generative-adversarial-network image-manipulation image-interpolation stylegan2 stylegan-encoder stylegan2-ada gan-inversion stylegan-inversion cvpr2022
Python
•
BSD 3-Clause "New" or "Revised" License
•13•116•8•0•Updated Nov 12, 2024Nov 12, 2024
robust-bayesian-recourse
Public
Robust Bayesian Recourse: a robust model-agnostic algorithmic recourse method (UAI'22)
machine-learning bayesian explainable-ai fairness-ml algorithmic-recourse distributionally-robust
Python
•
BSD 3-Clause "New" or "Revised" License
•1•2•0•0•Updated Nov 12, 2024Nov 12, 2024
tise-toolbox
Public
TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation (ECCV 2022)
evaluation-metrics text-to-image-synthesis language-and-vision toobox eccv2022
Python
•
BSD 3-Clause "New" or "Revised" License
•2•34•0•1•Updated Nov 12, 2024Nov 12, 2024
fsvc-ata
Public
Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments (ECCV 2022)
video-classification few-shot-learning appearance-alignment temporal-alignment
Python
•
BSD 3-Clause "New" or "Revised" License
•0•24•2•0•Updated Nov 12, 2024Nov 12, 2024
GeoFormer
Public
Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter (ECCV 2022)
instance-segmentation few-shot-learning 3d-point-cloud
Python
•
BSD 3-Clause "New" or "Revised" License
•5•29•2•1•Updated Nov 12, 2024Nov 12, 2024
Counting-DETR
Public
Few-shot Object Counting and Detection (ECCV 2022)
few-shot-learning object-counting few-shot-object-detection class-agnostic-detection few-shot-counting-and-detection few-shot-counting class-agnostic-counting
Python
•
BSD 3-Clause "New" or "Revised" License
•4•63•12•0•Updated Nov 12, 2024Nov 12, 2024
PSENet-Image-Enhancement
Public
PSENet: Progressive Self-Enhancement Network for Unsupervised Extreme-Light Image Enhancement (WACV 2023)
image-enhancement exposure-correction overexposure-correction lowlightenhancement wacv2023
Python
•
BSD 3-Clause "New" or "Revised" License
•8•59•4•0•Updated Nov 12, 2024Nov 12, 2024
ISBNet
Public
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution (CVPR 2023)
3d-point-clouds dynamic-convolution sparse-convolution 3d-instance-segmentation cvpr2023
Python
•
BSD 3-Clause "New" or "Revised" License
•25•126•24•1•Updated Nov 12, 2024Nov 12, 2024
GaPro
Public
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers (ICCV 2023)
3d-point-clouds dynamic-convolution weakly-supervised-learning box-detection 3d-instance-segmentation iccv2023
Python
•
BSD 3-Clause "New" or "Revised" License
•1•19•3•0•Updated Nov 12, 2024Nov 12, 2024
Open3DIS
Public
Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance (CVPR 2024)
3d-point-clouds 3d-instance-segmentation 3d-scene-understanding open-vocabulary cvpr2024
Python
•
BSD 3-Clause "New" or "Revised" License
•3•85•11•0•Updated Nov 12, 2024Nov 12, 2024
MagNet
Public
Progressive Semantic Segmentation (CVPR-2021)
python3 segmentation memory-efficiency high-resolution-image
Python
•
GNU Affero General Public License v3.0
•9•116•3•0•Updated Nov 11, 2024Nov 11, 2024
Warping-based_Backdoor_Attack-release
Public
WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)
security machine-learning computer-vision deep-learning backdoor-attacks deep-learning-security iclr2021
Python
•
GNU Affero General Public License v3.0
•17•114•3•0•Updated Nov 11, 2024Nov 11, 2024
RDUOT
Public
Official code for ECCV 2024 paper “A high-quality robust diffusion framework for corrupted dataset”
robust diffusion optimal-transport unbalanced-optimal-transport corrupted-dataset
Python
•
GNU Affero General Public License v3.0
•0•2•0•0•Updated Nov 1, 2024Nov 1, 2024
LFM
Public
Official PyTorch implementation of the paper: Flow Matching in Latent Space
generative-models latent-space diffusion-models vision-transformer conditional-normalizing-flows flow-matching
Python
•
GNU Affero General Public License v3.0
•9•226•5•0•Updated Oct 30, 2024Oct 30, 2024