Stars
nnInteractive is a framework for 3D interactive segmentation, supporting intuitive prompts like points, scribbles, bounding boxes, and lasso. Trained on 120+ diverse 3D datasets, it sets a new stan…
A PyTorch Library for Multi-Task Learning
Code for ICLR 2023 paper (Oral) — Towards Stable Test-Time Adaptation in Dynamic Wild World
Test-time Adaptation, Test-time Training and Source-free Domain Adaptation
[ECCV 2022] Learning Instance-Specific Adaptation for Cross-Domain Segmentation
Segment Anything for Microscopy
[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers
GPU Accelerated Building Blocks integrating HPC+AI for Energy Customers
Google Research
Implementation of Slot Attention from GoogleAI
Official pytorch repository for "Diffusion Posterior Sampling for General Noisy Inverse Problems"
This is the official implementation for the paper "SNR-aware low-light image enhancement" in CVPR2022
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
Deep Unfolding Network for Image Super-Resolution (CVPR, 2020) (PyTorch)
The official implementation of OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
TorchCFM: a Conditional Flow Matching library
Reopository for LPR CE4 data processing and filtering
Wavelet scattering transforms in Python with GPU acceleration
Variational Auto-Encoders in a Sequential Setting.
Image restoration with neural networks but without learning.
📻 Proof-of-concept project for detecting and classifying hyperbolas in ground penetrating radar (GPR) data.
[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-…