Related papers: GeoMIM: Towards Better 3D Knowledge Transfer via M…

We present a new pre-training strategy called M$^{3}$3D ($\underline{M}$ulti-$\underline{M}$odal $\underline{M}$asked $\underline{3D}$) built based on Multi-modal masked autoencoders that can leverage 3D priors and learned cross-modal…

The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Masked AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various…

Small CNN-based models usually require transferring knowledge from a large model before they are deployed in computationally resource-limited edge devices. Masked image modeling (MIM) methods achieve great success in various visual tasks…

The past year has witnessed a rapid development of masked image modeling (MIM). MIM is mostly built upon the vision transformers, which suggests that self-supervised visual representations can be done by masking input image parts while…

Vision-centric bird-eye-view (BEV) perception has shown promising potential in autonomous driving. Recent works mainly focus on improving efficiency or accuracy but neglect the challenges when facing environment changing, resulting in…

The combination of transformers and masked image modeling (MIM) pre-training framework has shown great potential in various vision tasks. However, the pre-training computational budget is too heavy and withholds the MIM from becoming a…

Accurate multi-view 3D object detection is essential for applications such as autonomous driving. Researchers have consistently aimed to leverage LiDAR's precise spatial information to enhance camera-based detectors through methods like…

We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with…

Image matching is a fundamental computer vision problem. While learning-based methods achieve state-of-the-art performance on existing benchmarks, they generalize poorly to in-the-wild images. Such methods typically need to train separate…

Accurate vessel segmentation in X-ray angiograms is crucial for numerous clinical applications. However, the scarcity of annotated data presents a significant challenge, which has driven the adoption of self-supervised learning (SSL)…

Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods either rely on expensive supervised learning with 3D…

Existing multi-view image compression methods often rely on 2D projection-based similarities between views to estimate disparities. While effective for small disparities, such as those in stereo images, these methods struggle with the more…

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

Multi-view image generation holds significant application value in computer vision, particularly in domains like 3D reconstruction, virtual reality, and augmented reality. Most existing methods, which rely on extending single images, face…

In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and…

LiDAR-based 3D detection has made great progress in recent years. However, the performance of 3D detectors is considerably limited when deployed in unseen environments, owing to the severe domain gap problem. Existing domain adaptive 3D…

Most Neural Radiance Fields (NeRFs) exhibit limited generalization capabilities, which restrict their applicability in representing multiple scenes using a single model. To address this problem, existing generalizable NeRF methods simply…

Remote sensing scene classification has been extensively studied for its critical roles in geological survey, oil exploration, traffic management, earthquake prediction, wildfire monitoring, and intelligence monitoring. In the past, the…

This paper proposes a GeneraLIst encoder-Decoder (GLID) pre-training method for better handling various downstream computer vision tasks. While self-supervised pre-training approaches, e.g., Masked Autoencoder, have shown success in…

3D perception tasks, such as 3D object detection and Bird's-Eye-View (BEV) segmentation using multi-camera images, have drawn significant attention recently. Despite the fact that accurately estimating both semantic and 3D scene layouts are…