Amir Arsalan Soltani's starred repositories

U-2-Net

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

Language:PythonLicense:Apache-2.0Stargazers:8190Issues:140Issues:336

MiDaS

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

Language:PythonLicense:MITStargazers:4153Issues:73Issues:237

SupContrast

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

Language:PythonLicense:BSD-2-ClauseStargazers:2932Issues:19Issues:132

contrastive-unpaired-translation

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

Language:PythonLicense:NOASSERTIONStargazers:2119Issues:35Issues:171

neuraloperator

Learning in infinite dimension with neural operators.

Language:PythonLicense:MITStargazers:1821Issues:38Issues:187

siren

Official implementation of "Implicit Neural Representations with Periodic Activation Functions"

Language:PythonLicense:MITStargazers:1682Issues:36Issues:58

torchsde

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Language:PythonLicense:Apache-2.0Stargazers:1492Issues:34Issues:73

gradslam

gradslam is an open source differentiable dense SLAM library for PyTorch

Language:PythonLicense:MITStargazers:1279Issues:47Issues:38

nvdiffrast

Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

Language:C++License:NOASSERTIONStargazers:1226Issues:26Issues:177

NVAE

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

Language:PythonLicense:NOASSERTIONStargazers:981Issues:16Issues:46

clean-fid

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

Language:PythonLicense:MITStargazers:878Issues:9Issues:46

torchsort

Fast, differentiable sorting and ranking in PyTorch

Language:PythonLicense:Apache-2.0Stargazers:745Issues:8Issues:61

blender-cli-rendering

Blender Python scripts for rendering images directly from command-line interface

Language:PythonLicense:GPL-3.0Stargazers:721Issues:20Issues:28

symbolic_deep_learning

Code for "Discovering Symbolic Models from Deep Learning with Inductive Biases"

Language:PythonLicense:MITStargazers:690Issues:28Issues:7

dna-3d-engine

3d engine implementation in DNA code!

siren

PyTorch implementation of Sinusodial Representation networks (SIREN)

Language:PythonLicense:MITStargazers:258Issues:8Issues:2

GrabNet

GrabNet: A Generative model to generate realistic 3D hands grasping unseen objects (ECCV2020)

Language:PythonLicense:NOASSERTIONStargazers:220Issues:13Issues:22

plan2explore

Repository for the paper "Planning to Explore via Self-Supervised World Models"

Language:PythonLicense:Apache-2.0Stargazers:210Issues:14Issues:4

Neural-Localization

Train an RL agent to localize actively (PyTorch)

hessian_penalty

Official Implementation of "The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement" (ECCV 2020 Spotlight)

Language:PythonLicense:BSD-2-ClauseStargazers:207Issues:12Issues:3

Generative-3D-Part-Assembly

Generative 3D Part Assembly via Dynamic Graph Learning, NeurIPS 2020

psdr-cuda

Path-space differentiable renderer

Language:C++License:BSD-3-ClauseStargazers:152Issues:8Issues:34

focal_calibration

Code for the paper "Calibrating Deep Neural Networks using Focal Loss"

Language:Jupyter NotebookLicense:MITStargazers:145Issues:8Issues:8

torch_tem

Implementation of the Tolman Eichenbaum Machine in pytorch

procedural_objects

blender based random procedural object generation for bullet grasping

Language:PythonLicense:MITStargazers:39Issues:3Issues:0

moog.github.io

Modular Object-Oriented Games (MOOG): Python-based game engine for reinforcement learning, psychology, and neurophysiology.

Language:PythonLicense:MITStargazers:33Issues:4Issues:1

unicornn

Official code for UnICORNN (ICML 2021)