Related papers: Single Point, Full Mask: Velocity-Guided Level Set…
Amodal segmentation is a challenging task that aims to predict the complete geometric shape of objects, including their occluded regions. Although existing methods primarily focus on amodal segmentation within the training domain, these…
Video amodal segmentation is a particularly challenging task in computer vision, which requires to deduce the full shape of an object from the visible parts of it. Recently, some studies have achieved promising performance by using motion…
Efficient trajectory planning in off-road terrains presents a formidable challenge for autonomous vehicles, often necessitating complex multi-step pipelines. However, traditional approaches exhibit limited adaptability in dynamic…
We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Existing vectorization methods operate under a modal paradigm:…
Segment Anything Model (SAM) has gained significant recognition in the field of semantic segmentation due to its versatile capabilities and impressive performance. Despite its success, SAM faces two primary limitations: (1) it relies…
Open-vocabulary semantic segmentation aims to assign pixel-level labels to images across an unlimited range of classes. Traditional methods address this by sequentially connecting a powerful mask proposal generator, such as the Segment…
Semi-supervised learning (SSL) has emerged as an effective paradigm for medical image segmentation, reducing the reliance on extensive expert annotations. Meanwhile, vision-language models (VLMs) have demonstrated strong generalization and…
Open-vocabulary semantic segmentation models aim to accurately assign a semantic label to each pixel in an image from a set of arbitrary open-vocabulary texts. In order to learn such pixel-level alignment, current approaches typically rely…
We present a model to reconstruct partially visible objects. The model takes a mask as an input, which we call weighted mask. The mask is utilized by gated convolutions to assign more weight to the visible pixels of the occluded instance…
Amodal segmentation aims to predict segmentation masks for both the visible and occluded regions of an object. Most existing works formulate this as a supervised learning problem, requiring manually annotated amodal masks or synthetic…
To fully understand the 3D context of a single image, a visual system must be able to segment both the visible and occluded regions of objects, while discerning their occlusion order. Ideally, the system should be able to handle any object…
Unsupervised Domain Adaptation has been an efficient approach to transferring the semantic segmentation model across data distributions. Meanwhile, the recent Open-vocabulary Semantic Scene understanding based on large-scale vision language…
As one of the most challenging and practical segmentation tasks, open-world semantic segmentation requires the model to segment the anomaly regions in the images and incrementally learn to segment out-of-distribution (OOD) objects,…
While nowadays deep neural networks achieve impressive performances on semantic segmentation tasks, they are usually trained by optimizing pixel-wise losses such as cross-entropy. As a result, the predictions outputted by such networks…
In this work, we demonstrate yet another approach to tackle the amodal segmentation problem. Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our target for amodal…
Reliable 3D segmentation is critical for understanding complex scenes with dense layouts and multi-scale objects, as commonly seen in industrial environments. In such scenarios, heavy occlusion weakens geometric boundaries between objects,…
Segmentation of indicated targets aids in the precise analysis of optical coherence tomography angiography (OCTA) samples. Existing segmentation methods typically perform on 2D projection targets, making it challenging to capture the…
Segment Anything (SAM) has recently pushed the boundaries of segmentation by demonstrating zero-shot generalization and flexible prompting after training on over one billion masks. Despite this, its mask prediction accuracy often falls…
Amodal perception requires inferring the full shape of an object that is partially occluded. This task is particularly challenging on two levels: (1) it requires more information than what is contained in the instant retina or imaging…
Amodal instance segmentation aims to predict the complete object mask including occluded regions that lack pixel-level observations and must be inferred with the aid of shape priors. Existing methods acquire shape priors through…