相关论文: Mask2Former for Video Instance Segmentation

Video object segmentation (VOS) is a critical task in the development of video perception and understanding. The Segment-Anything Model 2 (SAM 2), released by Meta AI, is the current state-of-the-art architecture for end-to-end VOS. SAM 2…

A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective. These labels require large human effort and for certain applications, such labels are not readily available. To…

We address the highly challenging problem of video object segmentation. Given only the initial mask, the task is to segment the target in the subsequent frames. In order to effectively handle appearance changes and similar background…

We propose an approach to instance-level image segmentation that is built on top of category-level segmentation. Specifically, for each pixel in a semantic category mask, its corresponding instance bounding box is predicted using a deep…

Instance segmentation of ships in synthetic aperture radar (SAR) imagery is critical for applications such as maritime monitoring, environmental analysis, and national security. SAR ship images present challenges including scale variation,…

In this report, we introduce our (pretty straightforard) two-step "detect-then-match" video instance segmentation method. The first step performs instance segmentation for each frame to get a large number of instance mask proposals. The…

Foundation models like the Segment Anything Model (SAM) have significantly advanced promptable image segmentation in computer vision. However, extending these capabilities to videos presents substantial challenges, particularly in ensuring…

In this work we propose a capsule-based approach for semi-supervised video object segmentation. Current video object segmentation methods are frame-based and often require optical flow to capture temporal consistency across frames which can…

In this work, we aim at building a simple, direct, and fast instance segmentation framework with strong performance. We follow the principle of the SOLO method of Wang et al. "SOLO: segmenting objects by locations". Importantly, we take one…

Visual effects (VFX) production often struggles with slow, resource-intensive mask generation. This paper presents an automated video segmentation pipeline that creates temporally consistent instance masks. It employs machine learning for:…

In this paper, we propose Contextual Guided Segmentation (CGS) framework for video instance segmentation in three passes. In the first pass, i.e., preview segmentation, we propose Instance Re-Identification Flow to estimate main properties…

Open-vocabulary 3D instance segmentation is cutting-edge for its ability to segment 3D instances without predefined categories. However, progress in 3D lags behind its 2D counterpart due to limited annotated 3D data. To address this, recent…

Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e.g., STEGO) or class-agnostic…

Segmenting an object in a video presents significant challenges. Each pixel must be accurately labelled, and these labels must remain consistent across frames. The difficulty increases when the segmentation is with arbitrary granularity,…

In this paper, we make the explicit connection between image segmentation methods and end-to-end diarization methods. From these insights, we propose a novel, fully end-to-end diarization model, EEND-M2F, based on the Mask2Former…

In contrast to fully supervised methods using pixel-wise mask labels, box-supervised instance segmentation takes advantage of simple box annotations, which has recently attracted increasing research attention. This paper presents a novel…

Video Object Segmentation and Tracking (VOST) presents a complex yet critical challenge in computer vision, requiring robust integration of segmentation and tracking across temporally dynamic frames. Traditional methods have struggled with…

The reliance on large labeled datasets presents a significant challenge in medical image segmentation. Few-shot learning offers a potential solution, but existing methods often still require substantial training data. This paper proposes a…

Weakly supervised instance segmentation has gained popularity because it reduces high annotation cost of pixel-level masks required for model training. Recent approaches for weakly supervised instance segmentation detect and segment objects…

Contemporary Video Instance Segmentation (VIS) methods typically adhere to a pre-train then fine-tune regime, where a segmentation model trained on images is fine-tuned on videos. However, the lack of temporal knowledge in the pre-trained…