Related papers: Flow-Guided Sparse Transformer for Video Deblurrin…
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…
Sparse-view reconstruction models typically require precise camera poses, yet obtaining these parameters from sparse-view images remains challenging. We introduce FreeSplatter, a scalable feed-forward framework that generates high-quality…
Image deblurring aims to restore a high-quality image from its corresponding blurred. The emergence of CNNs and Transformers has enabled significant progress. However, these methods often face the dilemma between eliminating long-range…
Recent advances have demonstrated the powerful capability of transformer architecture in image restoration. However, our analysis indicates that existing transformerbased methods can not establish both exact global and local dependencies…
Recent trackers adopt the Transformer to combine or replace the widely used ResNet as their new backbone network. Although their trackers work well in regular scenarios, however, they simply flatten the 2D features into a sequence to better…
Purpose: Tissue tracking is critical for downstream tasks in robot-assisted surgery. The Sparse Efficient Neural Depth and Deformation (SENDD) model has previously demonstrated accurate and real-time sparse point tracking, but struggled…
Image deblurring is a critical stage in mobile image signal processing pipelines, where the ability to restore fine structures and textures must be balanced with real-time constraints on edge devices. While recent deep networks such as…
Recently, Vision Transformers (ViTs) have attracted a lot of attention in the field of computer vision. Generally, the powerful representative capacity of ViTs mainly benefits from the self-attention mechanism, which has a high computation…
Recent progress in image deblurring techniques focuses mainly on operating in both frequency and spatial domains using the Fourier transform (FT) properties. However, their performance is limited due to the dependency of FT on stationary…
We present a deblurring method for scenes with occluding objects using a carefully designed layered blur model. Layered blur model is frequently used in the motion deblurring problem to handle locally varying blurs, which is caused by…
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…
Generative flow models offer powerful priors learned from large-scale natural images, but directly adapting them to restoration tasks such as motion deblurring causes severe fidelity degradation, as their training objective is inherently…
Remote sensing images are essential for many applications of the earth's sciences, but their quality can usually be degraded due to limitations in sensor technology and complex imaging environments. To address this, various remote sensing…
For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring…
Sparse-view scene reconstruction often faces significant challenges due to the constraints imposed by limited observational data. These limitations result in incomplete information, leading to suboptimal reconstructions using existing…
Diffusion-based video super-resolution (VSR) methods deliver strong perceptual quality but are often unsuitable for latency-sensitive scenarios due to reliance on future frames and expensive multi-step denoising. We propose Stream-DiffVSR,…
Diffusion model (DM) based Video Super-Resolution (VSR) approaches achieve impressive perceptual quality. However, they suffer from error accumulation, spatial artifacts, and a trade-off between perceptual quality and fidelity, primarily…
Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video…
Several state-of-the-art video deblurring methods are based on a strong assumption that the captured scenes are static. These methods fail to deblur blurry videos in dynamic scenes. We propose a video deblurring method to deal with general…
Unsupervised Video Object Segmentation (VOS) aims at identifying the contours of primary foreground objects in videos without any prior knowledge. However, previous methods do not fully use spatial-temporal context and fail to tackle this…