Related papers: SparseMeXT Unlocking the Potential of Sparse Repre…

Mesh-based simulations provide high-fidelity solutions to partial differential equations (PDEs), but achieving such accuracy typically requires fine meshes, leading to substantial computational overhead. Super-resolution techniques aim to…

3D occupancy infers fine-grained 3D geometry and semantics which is critical for autonomous driving. Most existing approaches carry high compute costs, requiring dense 3D feature volume and cross-attention to effectively aggregate…

The sparse cross-modality detector offers more advantages than its counterpart, the Bird's-Eye-View (BEV) detector, particularly in terms of adaptability for downstream tasks and computational cost savings. However, existing sparse…

While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling…

Neural network models are widely used in solving many challenging problems, such as computer vision, personalized recommendation, and natural language processing. Those models are very computationally intensive and reach the hardware limit…

Non-semantic features or semantic-agnostic features, which are irrelevant to image context but sensitive to image manipulations, are recognized as evidential to Image Manipulation Localization (IML). Since manual labels are impossible,…

The complexity of high-dimensional datasets presents significant challenges for machine learning models, including overfitting, computational complexity, and difficulties in interpreting results. To address these challenges, it is essential…

In this paper, we present a sparsity-aware deep network for automatic 4D facial expression recognition (FER). Given 4D data, we first propose a novel augmentation method to combat the data limitation problem for deep learning. This is…

Almost all previous deep learning-based multi-view stereo (MVS) approaches focus on improving reconstruction quality. Besides quality, efficiency is also a desirable feature for MVS in real scenarios. Towards this end, this paper presents a…

In this work we target the problem of estimating accurately localised correspondences between a pair of images. We adopt the recent Neighbourhood Consensus Networks that have demonstrated promising performance for difficult correspondence…

Emerging machine learning (ML) models (e.g., transformers) involve memory pin bandwidth-bound matrix-vector (MV) computation in inference. By avoiding pin crossings, processing in memory (PIM) can improve performance and energy for…

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue, one typically…

Traditional fluorescence staining is phototoxic to live cells, slow, and expensive; thus, the subcellular structure prediction (SSP) from transmitted light (TL) images is emerging as a label-free, faster, low-cost alternative. However,…

Recent advances in optimizing Gaussian Splatting for scene geometry have enabled efficient reconstruction of detailed surfaces from images. However, when input views are sparse, such optimization is prone to overfitting, leading to…

Neural implicit representations have revolutionized dense multi-view surface reconstruction, yet their performance significantly diminishes with sparse input views. A few pioneering works have sought to tackle the challenge of sparse-view…

While HDMaps are a crucial component of autonomous driving, they are expensive to acquire and maintain. Estimating these maps from sensors therefore promises to significantly lighten costs. These estimations however overlook existing…

Neighbour embeddings (NE) allow the representation of high dimensional datasets into lower dimensional spaces and are often used in data visualisation. In practice, accelerated approximations are employed to handle very large datasets.…

An image super-resolution method from multiple observation of low-resolution images is proposed. The method is based on sub-pixel accuracy block matching for estimating relative displacements of observed images, and sparse signal…

Neural Radiance Field (NeRF) significantly degrades when only a limited number of views are available. To complement the lack of 3D information, depth-based models, such as DSNeRF and MonoSDF, explicitly assume the availability of accurate…

Sparse algorithms offer great flexibility for multi-view temporal perception tasks. In this paper, we present an enhanced version of Sparse4D, in which we improve the temporal fusion module by implementing a recursive form of multi-frame…