Zijin Yin's starred repositories
segment-anything-2
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.
rectified-flow-pytorch
Implementation of rectified flow and some of its followup research / improvements in Pytorch
ControlNetPlus
ControlNet++: All-in-one ControlNet for image generations and editing!
OpticalFlow_Visualization
Python optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge
motion_guidance
Code for ICLR 2024 paper "Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators"
DenseFusion
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
Awesome-LLM-3D
Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources
lang-segment-anything
SAM with text prompt
DiffusionHandles
Diffusion Handles is a training-free method that enables 3D-aware image edits using a pre-trained Diffusion Model.
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.
GroundingDINO
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
DragAnything
[ECCV 2024] DragAnything: Motion Control for Anything using Entity Representation
DatasetExpansion
The repository of Expanding Small-Scale Datasets with Guided Imagination (NeurIPS 2023).
piecewise-rectified-flow
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator