zijinY

Zijin Yin's starred repositories

ProtoSeg

CVPR2022 (Oral) - Rethinking Semantic Segmentation: A Prototype View

Language:PythonMIT33700

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.

Language:Jupyter NotebookApache-2.0771100

Diffree

Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model

Language:PythonApache-2.013500

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

Language:PythonApache-2.01064500

rectified-flow-pytorch

Implementation of rectified flow and some of its followup research / improvements in Pytorch

Language:PythonMIT11200

ControlNetPlus

ControlNet++: All-in-one ControlNet for image generations and editing!

Language:PythonApache-2.0146200

OpticalFlow_Visualization

Python optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge

Language:PythonMIT41400

motion_guidance

Code for ICLR 2024 paper "Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators"

Language:Python8300

DenseFusion

DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception

Language:Python8100

Awesome-LLM-3D

Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources

MIT87800

ZoeDepth

Metric depth estimation from a single image

Language:Jupyter NotebookMIT215500

lang-segment-anything

SAM with text prompt

Language:Jupyter NotebookApache-2.0143800

DreamLIP

[ECCV 2024] Official PyTorch implementation of DreamLIP: Language-Image Pre-training with Long Captions

Language:Python7300

regmix

🧬 RegMix: Data Mixture as Regression for Language Model Pre-training

Language:Jupyter NotebookMIT5400

3D-VLA

[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model

Language:Python26400

DiffusionHandles

Diffusion Handles is a training-free method that enables 3D-aware image edits using a pre-trained Diffusion Model.

Language:Python1200

Object-Shadow-Generation-Dataset-DESOBAv2

[CVPR 2024] The dataset, code, and model for our paper "Shadow Generation for Composite Image Using Diffusion Model", CVPR, 2024.

Language:PythonApache-2.09200

Wonder3D

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

Language:PythonAGPL-3.0457800

GSVA

[CVPR2024] GSVA: Generalized Segmentation via Multimodal Large Language Models

3500

GroundingDINO

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Language:PythonApache-2.0586600

gRefCOCO

A benchmark dataset for GRES and GREC [CVPR2023 Highlight]

Language:Python17400

refer

Referring Expression Datasets API

Language:Jupyter NotebookApache-2.043500

DragAnything

[ECCV 2024] DragAnything: Motion Control for Anything using Entity Representation

Language:Python38600

PSALM

[ECCV2024] This is an official implementation for "PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model"

Language:PythonApache-2.016100

UnSAM

Code release for "Segment Anything without Supervision"

Language:Jupyter Notebook25700

DatasetExpansion

The repository of Expanding Small-Scale Datasets with Guided Imagination (NeurIPS 2023).

Language:Jupyter Notebook6900

dream-ood

source code for NeurIPS'23 paper "Dream the Impossible: Outlier Imagination with Diffusion Models"

Language:PythonNOASSERTION5800

DiffiT

[ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation

41300

GeoWizard

[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

Language:Python65800

piecewise-rectified-flow

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator

Language:Jupyter NotebookBSD-3-Clause37800