Related papers: SeisCoDE: 3D Seismic Interpretation Foundation Mod…
Implicit solvent models (ISMs) promise to deliver the accuracy of explicit solvent simulations at a fraction of the computational cost. However, despite decades of development, their accuracy has remained insufficient for many critical…
Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters. In the feature space, local regions within an individual…
Depth completion involves predicting dense depth maps from sparse LiDAR inputs. However, sparse depth annotations from sensors limit the availability of dense supervision, which is necessary for learning detailed geometric features. In this…
Semantic correspondence, the task of determining relationships between different parts of images, underpins various applications including 3D reconstruction, image-to-image translation, object tracking, and visual place recognition. Recent…
Semi-supervised learning (SSL) has emerged as a critical paradigm for medical image segmentation, mitigating the immense cost of dense annotations. However, prevailing SSL frameworks are fundamentally "inward-looking", recycling information…
Seismic interpretation is now serving as a fundamental tool for depicting subsurface geology and assisting activities in various domains, such as environmental engineering and petroleum exploration. However, most of the existing…
In recent years, pre-trained multimodal large models have attracted widespread attention due to their outstanding performance in various multimodal applications. Nonetheless, the extensive computational resources and vast datasets required…
Foundation model-based semantic transmission has recently shown great potential in wireless image communication. However, existing methods exhibit two major limitations: (i) they overlook the varying importance of semantic components for…
Self-Supervised Learning (SSL) has demonstrated promising results in 3D medical image analysis. However, the lack of high-level semantics in pre-training still heavily hinders the performance of downstream tasks. We observe that 3D medical…
Gaussian Splatting (GS) has recently marked a significant advancement in 3D reconstruction, delivering both rapid rendering and high-quality results. However, existing 3DGS methods pose challenges in understanding underlying 3D semantics,…
Seismic data interpolation is a critical pre-processing step for improving seismic imaging quality and remains a focus of academic innovation. To address the computational inefficiencies caused by extensive iterative resampling in current…
Contrastive learning methods in self-supervised settings have primarily focused on pre-training encoders, while decoders are typically introduced and trained separately for downstream dense prediction tasks. However, this conventional…
Recent developments in 3D vision have enabled significant progress in inferring neural fluid fields and realistic rendering of fluid dynamics. However, these methods require dense captures of real-world flows, which demand specialized…
In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks. The main innovation of the framework…
Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under…
Effectively parsing the facade is essential to 3D building reconstruction, which is an important computer vision problem with a large amount of applications in high precision map for navigation, computer aided design, and city generation…
Deep learning-based speech enhancement (SE) models have recently outperformed traditional techniques, yet their deployment on resource-constrained devices remains challenging due to high computational and memory demands. This paper…
Self-supervised learning (SSL) is capable of learning remarkable representations from centrally available data. Recent works further implement federated learning with SSL to learn from rapidly growing decentralized unlabeled images (e.g.,…
Geographical, physical, or economic constraints often result in missing traces within seismic data, making the reconstruction of complete seismic data a crucial step in seismic data processing. Traditional methods for seismic data…
Managing the dynamic regions in the photometric loss formulation has been a main issue for handling the self-supervised depth estimation problem. Most previous methods have alleviated this issue by removing the dynamic regions in the…