Related papers: FloorplanMAE:A self-supervised framework for compl…

Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations,…

Reconstructing building floor plans from point cloud data is key for indoor navigation, BIM, and precise measurements. Traditional methods like geometric algorithms and Mask R-CNN-based deep learning often face issues with noise, limited…

We present CAGE (Continuity-Aware edGE) network, a robust framework for reconstructing vector floorplans directly from point-cloud density maps. Traditional corner-based polygon representations are highly sensitive to noise and incomplete…

Buildings are a central feature of human culture and are increasingly being analyzed with computational methods. However, recent works on computational building understanding have largely focused on natural imagery of buildings, neglecting…

Masked image modeling (MIM) has been recognized as a strong self-supervised pre-training approach in the vision domain. However, the mechanism and properties of the learned representations by such a scheme, as well as how to further enhance…

Recently, self-supervised Masked Autoencoders (MAE) have attracted unprecedented attention for their impressive representation learning ability. However, the pretext task, Masked Image Modeling (MIM), reconstructs the missing local patches,…

Vision Transformer (ViT) suffers from data scarcity in semi-supervised learning (SSL). To alleviate this issue, inspired by masked autoencoder (MAE), which is a data-efficient self-supervised learner, we propose Semi-MAE, a pure ViT-based…

Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. However, subsequent works have complicated the framework with new auxiliary tasks or extra pre-trained models, inevitably…

Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised…

Metamaterials are emerging as a new paradigmatic material system to render unprecedented and tailorable properties for a wide variety of engineering applications. However, the inverse design of metamaterial and its multiscale system is…

Self-supervised learning with masked autoencoders has recently gained popularity for its ability to produce effective image or textual representations, which can be applied to various downstream tasks without retraining. However, we observe…

Masked autoencoder (MAE), a simple and effective self-supervised learning framework based on the reconstruction of masked image regions, has recently achieved prominent success in a variety of vision tasks. Despite the emergence of…

In the architectural design process, floor plan generation is inherently progressive and iterative. However, existing generative models for floor plans are predominantly end-to-end generation that produce an entire pixel-based layout in a…

In recent years, the foundation models have swept the computer vision field and facilitated the development of various tasks within different modalities. However, it remains an open question on how to design an infrared foundation model. In…

The ubiquity of missing data in urban intelligence systems, attributable to adverse environmental conditions and equipment failures, poses a significant challenge to the efficacy of downstream applications, notably in the realms of traffic…

This paper explores Masked Autoencoders (MAE) with Gaussian Splatting. While reconstructive self-supervised learning frameworks such as MAE learns good semantic abstractions, it is not trained for explicit spatial awareness. Our approach,…

Understanding vehicles in images is important for various applications such as intelligent transportation and self-driving system. Existing vehicle-centric works typically pre-train models on large-scale classification datasets and then…

Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios. Recently, contrastive learning and Transformer-based models have achieved good performance in many long-term series…

Self-supervised pre-training of image encoders is omnipresent in the literature, particularly following the introduction of Masked autoencoders (MAE). Current efforts attempt to learn object-centric representations from motion in videos. In…

Self-supervised learning (SSL) has recently emerged as a key strategy for building foundation models in remote sensing, where the scarcity of annotated data limits the applicability of fully supervised approaches. In this work, we introduce…