JiaqiLi404 / Super_resolution_DINO
The application of large pre-trained vision model DINOv2 from MetaAI for feature points matching, and a ViT decoder used for Auto Encoder
☆15Updated last year
Related projects: ⓘ
- ☆63Updated 9 months ago
- The official implementation of “Segment Anything Model is a Good Teacher for Local Feature Learning”.☆101Updated 11 months ago
- Fine-tuning dino v2 for semantic segmentation task on MSCOCO.☆15Updated last year
- Open-vocabulary Semantic Segmentation☆32Updated 7 months ago
- The official implementation of the paper The Change You Want to See (WACV 2023).☆49Updated 5 months ago
- Official Implementation for CVPR 2024 paper: CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor☆92Updated 2 months ago
- Unofficial edge detection implementation using the Automatic Mask Generation (AMG) of the Segment Anything Model (SAM).☆51Updated 5 months ago
- ☆87Updated 2 months ago
- The official implementation of the paper The Change You Want to See (Now in 3D) (ICCVW 2023).☆19Updated 2 months ago
- Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.☆52Updated 2 months ago
- DVIS: Decoupled Video Instance Segmentation Framework☆124Updated 5 months ago
- Official Implementation for "Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation", CVPR 2023.☆46Updated last year
- NIDS-Net: A unified framework for novel instance detection and segmentation☆35Updated 2 weeks ago
- [ICCV'23] Cascade-DETR: Delving into High-Quality Universal Object Detection☆93Updated last year
- Finetuning DINOv2 (https://github.com/facebookresearch/dinov2) on your own dataset☆35Updated last year
- Official pytorch implementation of DynaMask: Dynamic Mask Selection for Instance Segmentation (CVPR 2023)☆5Updated 6 months ago
- [CVPR 2024 Highlight] Official GraCo: Granularity-Controllable Interactive Segmentation.☆41Updated 2 months ago
- Official code for NetTrack [CVPR 2024]☆77Updated 6 months ago
- Using Segment-Anything and CLIP to generate pixel-aligned semantic features.☆31Updated last year
- [ACM MM23] CLIP-Count: Towards Text-Guided Zero-Shot Object Counting☆82Updated 6 months ago
- [NeurIPS 2023] FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models☆128Updated 9 months ago
- [ACM MM 2024] WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition☆36Updated 3 weeks ago
- ☆47Updated last year
- This repo contains the code for our paper Towards Open-Ended Visual Recognition with Large Language Model☆88Updated 2 months ago
- [ICLR 2024] DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation☆141Updated 3 months ago
- ☆67Updated 7 months ago
- [CVPR 2023] Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos☆46Updated 6 months ago
- ☆123Updated 8 months ago
- [CVPR 2024] Official implementation of "Universal Segmentation at Arbitrary Granularity with Language Instruction"☆75Updated 6 months ago
- (ICCV 2023) MasQCLIP for Open-Vocabulary Universal Image Segmentation☆30Updated 11 months ago