The rapid development of deep learning has made a great progress in image segmentation,
one of the fundamental tasks of computer vision. However, the current segmentation …

Visual semantic segmentation aims at separating a visual sample into diverse blocks with
specific semantic attributes and identifying the category for each block, and it plays a crucial …

Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a wo-stage
scheme. The general idea is to first generate class-agnostic region proposals and then feed …

Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In
contrast, synthetic data can be freely available using a generative model (eg, DALL-E …

Abstract 3D scene representations have gained immense popularity in recent years.
Methods that use Neural Radiance fields are versatile for traditional tasks such as novel …

In the field of visual scene understanding, deep neural networks have made impressive
advancements in various core tasks like segmentation, tracking, and detection. However …

Current deep networks are very data-hungry and benefit from training on large-scale
datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data …

Image segmentation is usually addressed by training a model for a fixed set of object
classes. Incorporating additional classes or more complex queries later is expensive as it …

Abstract Contrastive Language-Image Pre-training (CLIP) has made a remarkable
breakthrough in open-vocabulary zero-shot image recognition. Many recent studies …

Open-vocabulary scene understanding aims to localize and recognize unseen categories
beyond the annotated label space. The recent breakthrough of 2D open-vocabulary …