Related papers: Flow-Guided Sparse Transformer for Video Deblurrin…
Video super-resolution (VSR) is the task of restoring high-resolution frames from a sequence of low-resolution inputs. Different from single image super-resolution, VSR can utilize frames' temporal information to reconstruct results with…
Video deblurring is a challenging task that aims to recover sharp sequences from blur and noisy observations. The image-formation model plays a crucial role in traditional model-based methods, constraining the possible solutions. However,…
Since acquiring large amounts of realistic blurry-sharp image pairs is difficult and expensive, learning blind image deblurring from unpaired data is a more practical and promising solution. Unfortunately, dominant approaches rely heavily…
3D Gaussian Splatting (3D-GS) has demonstrated exceptional capabilities in 3D scene reconstruction and novel view synthesis. However, its training heavily depends on high-quality, sharp images and accurate camera poses. Fulfilling these…
Although Transformers have successfully transitioned from their language modelling origins to image-based applications, their quadratic computational complexity remains a challenge, particularly for dense prediction. In this paper we…
Low-light image enhancement aims to restore the visibility of images captured by visual sensors in dim environments by addressing their inherent signal degradations, such as luminance attenuation and structural corruption. Although numerous…
Motion blur in scene text images severely impairs readability and hinders the reliability of computer vision tasks, including autonomous driving, document digitization, and visual information retrieval. Conventional deblurring approaches…
In this paper, we introduce a novel image-goal navigation approach, named RFSG. Our focus lies in leveraging the fine-grained connections between goals, observations, and the environment within limited image data, all the while keeping the…
Pose-guided person image generation is to transform a source person image to a target pose. This task requires spatial manipulations of source data. However, Convolutional Neural Networks are limited by the lack of ability to spatially…
In low-light conditions, capturing videos with frame-based cameras often requires long exposure times, resulting in motion blur and reduced visibility. While frame-based motion deblurring and low-light enhancement have been studied, they…
We introduce a new attention mechanism, dubbed structural self-attention (StructSA), that leverages rich correlation patterns naturally emerging in key-query interactions of attention. StructSA generates attention maps by recognizing…
Real-time monocular 3D reconstruction is a challenging problem that remains unsolved. Although recent end-to-end methods have demonstrated promising results, tiny structures and geometric boundaries are hardly captured due to their…
Recently, deep learning based video super-resolution (SR) methods have achieved promising performance. To simultaneously exploit the spatial and temporal information of videos, employing 3-dimensional (3D) convolutions is a natural…
Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the models grow gigantic…
This paper presents a comprehensive study and improvement of the Restormer architecture for high-resolution image motion deblurring. We introduce architectural modifications that reduce model complexity by 18.4% while maintaining or…
Digital subtraction angiography (DSA) is a key imaging technique for the auxiliary diagnosis and treatment of cerebrovascular diseases. Recent advancements in gaussian splatting and dynamic neural representations have enabled robust 3D…
Scene flow enables an understanding of the motion characteristics of the environment in the 3D world. It gains particular significance in the long-range, where object-based perception methods might fail due to sparse observations far away.…
Taking photographs ''in-the-wild'' is often hindered by fence obstructions that stand between the camera user and the scene of interest, and which are hard or impossible to avoid. De-fencing is the algorithmic process of automatically…
Stereo videos for the dynamic scenes often show unpleasant blurred effects due to the camera motion and the multiple moving objects with large depth variations. Given consecutive blurred stereo video frames, we aim to recover the latent…
Single-shot image deblurring in a low-light condition is known to be a profoundly challenging image translation task. This study tackles the limitations of the low-light image deblurring with a learning-based approach and proposes a novel…