There are 3 repositories under video-instance-segmentation topic.
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval
[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale
Next-generation Video instance recognition framework on top of Detectron2 which supports InstMove (CVPR 2023), SeqFormer(ECCV Oral), and IDOL(ECCV Oral))
Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight
Mask-Free Video Instance Segmentation [CVPR 2023]
SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV 2022 Oral)
[NeurIPS'21] Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking and Segmentation (MOTS), Pose Tracking, Video Instance Segmentation (VIS), and class-agnostic MOT (e.g. TAO dataset).
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)
Temporally Efficient Vision Transformer for Video Instance Segmentation, CVPR 2022, Oral
Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency (AAAI 2021)
Code release for "UniVS: Unified and Universal Video Segmentation with Prompts as Queries" (CVPR2024)
DVIS: Decoupled Video Instance Segmentation Framework
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation
Code release for "STMask: Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation"(CVPR2021)
Awesome video instance segmentation papers
Open-vocabulary Video Instance Segmentation Codebase built upon Detectron2, which is really easy to use.
Code release for "MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos"(CVPR2023)
[CVPRW 2021] - Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation
[CVPR 2021] Youtube-VIS 2021 3rd place, [CVPR 2020] winner DAVIS 2020. Code for mask selection based methods.
UNOFFICIAL implement of MaskTrackRCNN for video instance segmentation via mmdetection 2.11.0.
A video instance segmentation codebase based on OpenMMLab projects.
Implementation of joint construction of Mask/BBox heads in QDTrack-mots for joint training research
This repository captures our work on Video Instance Segmentation, as a part of our CS 534 AI course project, under Prof. Jacob Whitehill. We describe and analyze the experimental trials performed on the baseline ([CVPRW 2021] - Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation).
Dynamic MNIST digit sequences for video instance segmentation with optical flow data.
This repo contains fixes for MaskTrackRCNN paper to make it compatible on PyTorch 1.6+.
The repository for TLTM: Two-Level Temporal Relation Model for Online Video Instance Segmentation.
CenterMask is powered with MaskTrackRCNN tracking algorithm for video instance segmentation.