Niki Amini-Naieni

GECO2. Official implementation of GeCo2 (AAAI 2026) -- Generalized-Scale Object Counting with Gradual Query Aggregation

audio-counting. Class-Agnostic Audio Repetition Counting

PrACo. Jupyter Notebook

blood-cell-detection-dataset. WBC & RBC detection dataset from peripheral blood smears. https://aslan.md/blood-cell-detection-dataset/

CountGDPlusPlus. Includes the code for training and testing the CountGD++ model from the paper CountGD++: Generalized Prompting for Open-World Counting.

PairTally_Benchmark. [DICTA25] PairTally: Benchmarking Fine-Grained Visual Counting

practicals. VGG computer vision practicals

Seed1.5-VL. Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

DAVE. Python

ABC123. Python

annolid. An annotation and instance segmentation-based multi-object tracking and behavior analysis package.

CountVid. Includes the VideoCount dataset and CountVid code for the paper Open-World Object Counting in Videos.

referring-expression-counting. Python

GeCo. Python

OVT-B-Dataset. [NeurIPS 2024] Repository for the paper "OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking".

label-delay-cl. The codebase to reimplement the results from Label Delay in Continual Learning

sam2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

MultimodalUniverse. Large-Scale Multimodal Dataset of Astronomical Data

BeeAlarmed. A camera based bee-hive monitoring that identifies and tracks bees. It also identifies bee characteristics with a neural network, such as pollen packages, wasps, varroa mite infestations or bees trying to cool the hive.

instantcalibration. Includes the code for the paper: Instant Uncertainty Calibration of NeRFs Using a Meta-Calibrator (ECCV 2024)

instantcalibration.github.io. HTML

switch-cuda. A simple bash script for switching between installed versions of CUDA.

gradio-image-prompter. Image Prompter for Gradio

CountGD. Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.

masa. Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything

infinigen. Infinite Photorealistic Worlds using Procedural Generation

Open-GroundingDino. This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

NeRP. Implicit Neural Representation Learning With Prior Embedding for Sparsely Sampled Image Reconstruction

LearningToCountEverything. Python

loca. LOCA - A Low-Shot Object Counting Network With Iterative Prototype Adaptation (ICCV 2023)

SelfCollages. Learning to Count without Annotations

open_clip. An open source implementation of CLIP.

CounTX. Includes FSC-147-D and the code for training and testing the CounTX model from the paper Open-world Text-specified Object Counting.

HashNeRF-pytorch. Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives: https://nvlabs.github.io/instant-ngp/

slurm_web. Website-based resource monitor for Slurm system

BayesRays. Official Code for Bayes' Rays Paper

RePaint-Inpainting-using-Denoising-Diffusion-Probabilistic-Models. Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022

FlipNeRF. [ICCV2023] FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis

CounTX_Berry. Python

perfectly-secure-steganography. Contains open source code for the paper "Perfectly-secure Steganography using Minimum Entropy Coupling"

CF-NeRF. [ECCV 2022] Official code release of Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification

deep-image-prior. Image restoration with neural networks but without learning.

wilds. A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.

peltier_chip_model. This repository includes code in Julia that can be used to model the behavior of any Peltier chip well given twenty experimental data points that are often provided by Peltier chip manufacturers. To easily take users through the code, it is in the format of a Jupyter notebook.