Related papers: Flow-Guided Sparse Transformer for Video Deblurrin…
Video deblurring is a highly under-constrained problem due to the spatially and temporally varying blur. An intuitive approach for video deblurring includes two steps: a) detecting the blurry region in the current frame; b) utilizing the…
The quadratic time and memory complexity of the attention mechanism in modern Transformer based video generators makes end-to-end training for ultra high resolution videos prohibitively expensive. Motivated by this limitation, we introduce…
Few-Shot Video Object Segmentation (FSVOS) aims to segment objects in a query video with the same category defined by a few annotated support images. However, this task was seldom explored. In this work, based on IPMT, a state-of-the-art…
As the number of video content has mushroomed in recent years, automatic video summarization has come useful when we want to just peek at the content of the video. However, there are two underlying limitations in generic video summarization…
3D Gaussian splatting enables high-quality novel view synthesis (NVS) at real-time frame rates. However, its quality drops sharply as we depart from the training views. Thus, dense captures are needed to match the high-quality expectations…
Rendering high-fidelity images from sparse point clouds is still challenging. Existing learning-based approaches suffer from either hole artifacts, missing details, or expensive computations. In this paper, we propose a novel framework to…
Attention mechanism has gained huge popularity due to its effectiveness in achieving high accuracy in different domains. But attention is opportunistic and is not justified by the content or usability of the content. Transformer like…
Deformable Gaussian Splatting (GS) accomplishes photorealistic dynamic 3-D reconstruction from dense multi-view video (MVV) by learning to deform a canonical GS representation. However, in filmmaking, tight budgets can result in sparse…
Existing approaches to increasing the effective depth of Transformers predominantly rely on parameter reuse, extending computation through recursive execution. Under this paradigm, the network structure remains static along the training…
Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference. Traditional deblurring algorithms leverage the physics of the image formation model and use hand-crafted priors: they usually produce…
To manage the complexity of transformers in video compression, local attention mechanisms are a practical necessity. The common approach of partitioning frames into patches, however, creates architectural flaws like irregular receptive…
Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion},…
The great potential of unsupervised monocular depth estimation has been demonstrated by many works due to low annotation cost and impressive accuracy comparable to supervised methods. To further improve the performance, recent works mainly…
Language-guided robotic grasping is a rapidly advancing field where robots are instructed using human language to grasp specific objects. However, existing methods often depend on dense camera views and struggle to quickly update scenes,…
While single-image super-resolution (SISR) has attracted substantial interest in recent years, the proposed approaches are limited to learning image priors in order to add high frequency details. In contrast, multi-frame super-resolution…
Image deblurring aims to reconstruct a latent sharp image from its corresponding blurred one. Although existing methods have achieved good performance, most of them operate exclusively in either the spatial domain or the frequency domain,…
Video diffusion Transformer (DiT) models excel in generative quality but hit major computational bottlenecks when producing high-resolution, long-duration videos. The quadratic complexity of full attention leads to prohibitively high…
Multi-scale (MS) approaches have been widely investigated for blind single image / video deblurring that sequentially recovers deblurred images in low spatial scale first and then in high spatial scale later with the output of lower scales.…
One of the key components for video deblurring is how to exploit neighboring frames. Recent state-of-the-art methods either used aligned adjacent frames to the center frame or propagated the information on past frames to the current frame…
Sparse representation has recently been successfully applied in visual tracking. It utilizes a set of templates to represent target candidates and find the best one with the minimum reconstruction error as the tracking result. In this…