Related papers: Raformer: Redundancy-Aware Transformer for Video W…

The recently developed pure Transformer architectures have attained promising accuracy on point cloud learning benchmarks compared to convolutional neural networks. However, existing point cloud Transformers are computationally expensive…

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…

This paper proposes a Robust and Efficient Memory Network, referred to as REMN, for studying semi-supervised video object segmentation (VOS). Memory-based methods have recently achieved outstanding VOS performance by performing non-local…

Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computations in order to compete with convolutional neural networks…

Full-waveform inversion (FWI) is an advanced technique for reconstructing high-resolution subsurface physical parameters by progressively minimizing the discrepancy between observed and predicted seismic data. However, conventional FWI…

This paper presents a powerful framework to customize video creations by incorporating multiple specific identity (ID) photos, with video diffusion Transformers, referred to as Ingredients. Generally, our method consists of three primary…

Video inpainting involves modifying local regions within a video, ensuring spatial and temporal consistency. Most existing methods focus primarily on scene completion (i.e., filling missing regions) and lack the capability to insert new…

Image registration is a crucial task in signal processing, but it often encounters issues with stability and efficiency. Non-learning registration approaches rely on optimizing similarity metrics between fixed and moving images, which can…

Recently, the deep learning technology has been successfully applied in the field of image compression, leading to superior rate-distortion performance. However, a challenge of many learning-based approaches is that they often achieve…

Diffusion models have achieved remarkable success in image generation, with applications broadening across various domains. Inpainting is one such application that can benefit significantly from diffusion models. Existing methods either…

In NeRF-aided editing tasks, object movement presents difficulties in supervision generation due to the introduction of variability in object positions. Moreover, the removal operations of certain scene objects often lead to empty regions,…

The past year has witnessed the rapid development of applying the Transformer module to vision problems. While some researchers have demonstrated that Transformer-based models enjoy a favorable ability of fitting data, there are still…

Many existing video inpainting algorithms utilize optical flows to construct the corresponding maps and then propagate pixels from adjacent frames to missing areas by mapping. Despite the effectiveness of the propagation mechanism, they…

Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn this observation into VSA, a trainable, hardware-efficient…

Over the last few years, the performance of inpainting to fill missing regions has shown significant improvements by using deep neural networks. Most of inpainting work create a visually plausible structure and texture, however, due to them…

This work introduces Differential Wavelet Amplifier (DWA), a drop-in module for wavelet-based image Super-Resolution (SR). DWA invigorates an approach recently receiving less attention, namely Discrete Wavelet Transformation (DWT). DWT…

Vision-based Transformer have shown huge application in the perception module of autonomous driving in terms of predicting accurate 3D bounding boxes, owing to their strong capability in modeling long-range dependencies between the visual…

Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on…

Transformer-based video diffusion models (VDMs) deliver state-of-the-art video generation quality but are constrained by the quadratic cost of self-attention, making long sequences and high resolutions computationally expensive. While…

Masked Video Autoencoder (MVA) approaches have demonstrated their potential by significantly outperforming previous video representation learning methods. However, they waste an excessive amount of computations and memory in predicting…