AImageLab

art2real

Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image Translation. CVPR 2019

dress-code

Dress Code: High-Resolution Multi-Category Virtual Try-On. ECCV 2022

LLaVA-MORE

[ICCVW 25] LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning

mammoth

An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning

meshed-memory-transformer

Meshed-Memory Transformer for Image Captioning. CVPR 2020

multimodal-garment-designer

This is the official repository for the paper "Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing". ICCV 2023

novelty-detection

Latent space autoregression for novelty detection.

show-control-and-tell

Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions. CVPR 2019

VATr

VKD

PyTorch code for ECCV 2020 paper: "Robust Re-Identification by Multiple Views Knowledge Distillation"

aimagelab/mammoth

An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning

aimagelab/LLaVA-MORE

[ICCVW 25] LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning

aimagelab/pacscore

[CVPR 2023 & IJCV 2025] Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

aimagelab/awesome-human-visual-attention

This repository contains a curated list of research papers and resources focusing on saliency and scanpath prediction, human attention, human visual search.

aimagelab/ReflectiVA

[CVPR 2025] Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering

aimagelab/CoDE

[ECCV'24] Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

aimagelab/Alfie

Democratising RGBA Image Generation With No $$$ (AI4VA@ECCV24)

aimagelab/HySAC

Hyperbolic Safety-Aware Vision-Language Models. CVPR 2025

aimagelab/ReT

[CVPR 2025] Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval

aimagelab/awesome-captioning-evaluation

[IJCAI 2025] Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives

aimagelab/TransFusion

Official codebase of "Update Your Transformer to the Latest Release: Re-Basin of Task Vectors" - ICML 2025

aimagelab/MaPeT

Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training

aimagelab/MAD

Official PyTorch implementation for "Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas", presenting the Merge-Attend-Diffuse operator (ECCV24)

aimagelab/FourBi

Binarizing Documents by Leveraging both Space and Frequency. (ICDAR 2024)

aimagelab/ScanDiff

This is the official repository for the paper "Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction". ICCV 2025

aimagelab/Emuru-autoregressive-text-img

Official PyTorch implementation for "Zero-Shot Styled Text Image Generation, but Make It Autoregressive" (CVPR25)

aimagelab/MissRAG

[ICCV 2025] MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models

aimagelab/COGT

[ICLR 2025] Causal Graphical Models for Vision-Language Compositional Understanding

aimagelab/DICE

[ICCV 2025] What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models

aimagelab/ReT-2

Recurrence Meets Transformers for Universal Multimodal Retrieval

aimagelab/fed-mammoth

General Federated Continual Learning Framework

aimagelab/mammoth-lite

aimagelab/CHAIR-DPO

[BMVC 2025] Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization

aimagelab/DitHub

aimagelab/MLLMs-FlowTracker

[CAIP 2025] Tracing Information Flow in LLaMA Vision: A Step Toward Multimodal Understanding

aimagelab/itserr-wp8-latin-embeddings

ITSERR WP8 - Code for Latin embeddings semantic search

aimagelab/Sanctuaria-Gaze

Sanctuaria-Gaze is a multimodal dataset of egocentric recordings from visits to four sanctuaries in Northern Italy. Alongside the data, we release an open-source framework for automatic detection and analysis of Areas of Interest (AOIs), enabling gaze-based research in dynamic, real-world settings without manual annotation.

aimagelab/biblical-retrieval-synthesis

[TPDL 2025] Generating Synthetic Data with Large Language Models for Low-Resource Sentence Retrieval

aimagelab/coldfront

HPC Resource Allocation System

aimagelab/synthcap_pp

Official implementation of "Augmenting and Mixing Transformers with Synthetic Data for Image Captioning"