Reference PyTorch implementation and models for DINOv3

Image to image style transfer with LoRA fine-tuning on diffusion model

An adversarial example library for constructing attacks, building defenses, and benchmarking both

Official implementations for paper: Zero-shot Image Editing with Reference Imitation

[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official Implementation)

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

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering (nvidia)

Offical codes for "AutoVFX: Physically Realistic Video Editing from Natural Language Instructions."

Directed Diffusion: Direct Control of Object Placement through Attention Guidance (AAAI2024)

[CVPR 2024] code release for "DiffusionLight: Light Probes for Free by Painting a Chrome Ball"

Official implementation for the paper "InsertDiffusion: Identity Preserving Visualization of Objects through a Training-Free Diffusion Architecture".

The codes of our paper "ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion"

Implementation of Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models

Code for "Perspective Aware Road Obstacle Detection"

Copy-paste augmentation for segmentation and detection tasks

Image composition toolbox: everything you want to know about image composition or object insertion

A curated list of papers, code and resources pertaining to image composition/compositing or object insertion/addition/compositing, which aims to generate realistic composite image.

[AAAI 2021] EMLight: Lighting Estimation via Spherical Distribution Approximation, [TIP] GMLight: Lighting Estimation via Geometric Distribution Approximation

eCommerce_tailwind_template (Html,css,js,tailwind)

eCommerce Next.js Application

[NeurIPS 2023] 3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

[NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

This work is the part of the environmental project during my time at Fujairah Research Center, Fujairah Environment Authority, UAE

You can do anything by sota AI with prompt ,auto AI tools , VL larger model fine and project

Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation

Code for CVPR2024 'Segment Every Out-of-Distribution Object '

[ECCV 2024]The official code of ECCV'24 paper "Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenes"

Official implementation for Hierarachical Diffusion Model in CVPR24 Template free reconstruction of human object interaction

DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors

"IMoS: Intent-Driven Fullbody Motion Synthesis for Human-Object Interaction". Proceeding of EUROGRAPHICS 2023.