Related papers: Enhancing Multi-Scale Implicit Learning in Image S…

Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood. Modern PE methods such as RoPE still struggle on tasks…

We propose a novel positional encoding for learning graph on Transformer architecture. Existing approaches either linearize a graph to encode absolute position in the sequence of nodes, or encode relative position with another node using…

Face inpainting requires the model to have a precise global understanding of the facial position structure. Benefiting from the powerful capabilities of deep learning backbones, recent works in face inpainting have achieved decent…

Recent advances show that semi-supervised implicit representation learning can be achieved through physical constraints like Eikonal equations. However, this scheme has not yet been successfully used for LiDAR point cloud data, due to its…

Partitioning an image into superpixels based on the similarity of pixels with respect to features such as colour or spatial location can significantly reduce data complexity and improve subsequent image processing tasks. Initial algorithms…

The many variations of Implicit Neural Representations (INRs), where a neural network is trained as a continuous representation of a signal, have tremendous practical utility for downstream tasks including novel view synthesis, video…

Recent advances in Transformer models allow for unprecedented sequence lengths, due to linear space and time complexity. In the meantime, relative positional encoding (RPE) was proposed as beneficial for classical Transformers and consists…

Implicit neural representations (INRs) have arisen as useful methods for representing signals on Euclidean domains. By parameterizing an image as a multilayer perceptron (MLP) on Euclidean space, INRs effectively represent signals in a way…

In this paper, we address the challenge of making ViT models more robust to unseen affine transformations. Such robustness becomes useful in various recognition tasks such as face recognition when image alignment failures occur. We propose…

Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former…

Although large language models (LLMs) have achieved significant progress in handling long-context inputs, they still suffer from the ``lost-in-the-middle'' problem, where crucial information in the middle of the context is often…

This paper presents a pixel selection method for compact image representation based on superpixel segmentation and tensor completion. Our method divides the image into several regions that capture important textures or semantics and selects…

Rotary Position Embedding (RoPE) is the de facto positional encoding in large language models due to its ability to encode relative positions and support length extrapolation. When adapted to vision transformers, the standard axial…

Co-occurrent visual pattern makes aggregating contextual information a common paradigm to enhance the pixel representation for semantic image segmentation. The existing approaches focus on modeling the context from the perspective of the…

Guided depth super-resolution is a practical task where a low-resolution and noisy input depth map is restored to a high-resolution version, with the help of a high-resolution RGB guide image. Existing methods usually view this task as a…

Vector quantization approaches (VQ-VAE, VQ-GAN) learn discrete neural representations of images, but these representations are inherently position-dependent: codes are spatially arranged and contextually entangled, requiring autoregressive…

Deep representations across modalities are inherently intertwined. In this paper, we systematically analyze the spectral characteristics of various semantic and pixel encoders. Interestingly, our study uncovers a highly inspiring and rarely…

Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning…

Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuous domain functions realized by a neural network taking…

Single-image super-resolution (SISR) is a canonical problem with diverse applications. Leading methods like SRGAN produce images that contain various artifacts, such as high-frequency noise, hallucinated colours and shape distortions, which…