Related papers: Bidirectional Feature-aligned Motion Transformatio…
High-efficient image compression is a critical requirement. In several scenarios where multiple modalities of data are captured by different sensors, the auxiliary information from other modalities are not fully leveraged by existing…
To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, and depth. However, multimodal data often suffer from the position shift problem, i.e., the image…
Recently, deep learning methods have shown promising results in point cloud compression. For octree-based point cloud compression, previous works show that the information of ancestor nodes and sibling nodes are equally important for…
We propose a method for joint detection and tracking of multiple objects in 3D point clouds, a task conventionally treated as a two-step process comprising object detection followed by data association. Our method embeds both steps into a…
We propose an intra frame predictive strategy for compression of 3D point cloud attributes. Our approach is integrated with the region adaptive graph Fourier transform (RAGFT), a multi-resolution transform formed by a composition of…
In cardiac CINE, motion-compensated MR reconstruction (MCMR) is an effective approach to address highly undersampled acquisitions by incorporating motion information between frames. In this work, we propose a novel perspective for…
Thanks to the application of deep learning technology in point cloud processing of the remote sensing field, point cloud segmentation has become a research hotspot in recent years, which can be applied to real-world 3D, smart cities, and…
Discrete transforms play an important role in many signal processing applications, and low-complexity alternatives for classical transforms became popular in recent years. Particularly, the discrete cosine transform (DCT) has proven to be…
We rethink the role of positional encoding in 3D representation learning and fine-tuning. We argue that using positional encoding in point Transformer-based methods serves to aggregate multi-scale features of point clouds. Additionally, we…
Three-dimensional point clouds can be viewed as discrete samples of smooth manifolds, allowing spectral analysis using the Laplace-Beltrami operator (LBO). However, the traditional point cloud manifold harmonic transform (PMHT) is limited…
Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often mapped to a compact semantic embedding, which is then compressed and transmitted for…
Current region feature-based image captioning methods have progressed rapidly and achieved remarkable performance. However, they are still prone to generating irrelevant descriptions due to the lack of contextual information and the…
Cone-beam CT (CBCT) provides on-board volumetric anatomy for image guidance and treatment adaptation in radiotherapy. To compensate for respiration-induced anatomical motion, time-resolved CBCT is highly desired to capture the…
Limited labeled data makes it hard to train models from scratch in medical domain, and an important paradigm is pre-training and then fine-tuning. Large pre-trained models contain rich representations, which can be adapted to downstream…
Previous studies have demonstrated the effectiveness of point-based neural models on the point cloud analysis task. However, there remains a crucial issue on producing the efficient input embedding for raw point coordinates. Moreover,…
Deformable image registration (DIR) is a crucial and challenging technique for aligning anatomical structures in medical images and is widely applied in diverse clinical applications. However, existing approaches often struggle to capture…
Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective, these methods usually treat adaptation as a discrete…
Existing distribution compression methods reduce the number of observations in a dataset by minimising the Maximum Mean Discrepancy (MMD) between original and compressed sets, but modern datasets are often large in both sample size and…
Motion estimation of organs in a sequence of images is important in numerous medical imaging applications. The focus of this paper is the analysis of 4D Respiratory Correlated Computed Tomography (RCCT) Imaging. It is hypothesized that the…
Recent advances in extreme image compression have revealed that mapping pixel data into highly compact latent representations can significantly improve coding efficiency. However, most existing methods compress images into 2-D latent spaces…