D.P's starred repositories
semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
Grounded-Segment-Anything
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
the-algorithm-ml
Source code for Twitter's Recommendation Algorithm
VLM_survey
Collection of AWESOME vision-language models for vision tasks
Semantic-SAM
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"
comfyui_controlnet_aux
ComfyUI's ControlNet Auxiliary Preprocessors
EfficientSAM
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Semantic-Segment-Anything
Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).
PatchFusion
[CVPR 2024] An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation
GaussianObject
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting (SIGGRAPH Asia 2024, TOG)
ComfyUI-Marigold
Marigold depth estimation in ComfyUI
useful-transformers
Efficient Inference of Transformer models
panoptic-segment-anything
Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation
matplotlib-backend-kitty
show matplotlib plots directly in your kitty terminal
depth_segmentation
A collection of segmentation methods working on depth images
Siamese-Neural-Networks-for-One-shot-Image-Recognition
One-shot Siamese Neural Network, using TensorFlow 2.0, based on the work presented by Gregory Koch, Richard Zemel, and Ruslan Salakhutdinov. we used the “Labeled Faces in the Wild” dataset with over 5,700 different people. Some people have a single image, while others have dozens.
ssl-sonar-images
Code for our paper Self-supervised Learning for Sonar Image Classification [CVPR 2022]