Related papers: StabStitch++: Unsupervised Online Video Stitching …
Most classical SLAM systems rely on the static scene assumption, which limits their applicability in real world scenarios. Recent SLAM frameworks have been proposed to simultaneously track the camera and moving objects. However they are…
We study the problem of image alignment for panoramic stitching. Unlike most existing approaches that are feature-based, our algorithm works on pixels directly, and accounts for errors across the whole images globally. Technically, we…
The spike camera, with its high temporal resolution, low latency, and high dynamic range, addresses high-speed imaging challenges like motion blur. It captures photons at each pixel independently, creating binary spike streams rich in…
Depth super-resolution has achieved impressive performance, and the incorporation of multi-frame information further enhances reconstruction quality. Nevertheless, statistical analyses reveal that video depth super-resolution remains…
In this paper, we explore a new domain for video-to-video translation. Motivated by the availability of animation movies that are adopted from illustrated books for children, we aim to stylize these videos with the style of the original…
Neuromorphic vision sensors (event cameras) simulate biological visual perception systems and have the advantages of high temporal resolution, less data redundancy, low power consumption, and large dynamic range. Since both events and…
Existing video stabilization methods often generate visible distortion or require aggressive cropping of frame boundaries, resulting in smaller field of views. In this work, we present a frame synthesis algorithm to achieve full-frame video…
Large pretrained plain vision Transformers (ViTs) have been the workhorse for many downstream tasks. However, existing works utilizing off-the-shelf ViTs are inefficient in terms of training and deployment, because adopting ViTs with…
Spatio-temporal representational learning has been widely adopted in various fields such as action recognition, video object segmentation, and action anticipation. Previous spatio-temporal representational learning approaches primarily…
Weakly supervised video object segmentation (WSVOS) enables the identification of segmentation maps without requiring an extensive training dataset of object masks, relying instead on coarse video labels indicating object presence. Current…
Video stabilization remains a fundamental problem in computer vision, particularly pixel-level synthesis solutions for video stabilization, which synthesize full-frame outputs, add to the complexity of this task. These methods aim to…
Understanding how visual information is encoded in biological and artificial systems often requires vision scientists to generate appropriate stimuli to test specific hypotheses. Although deep neural network models have revolutionized the…
Video-language alignment is a crucial multi-modal task that benefits various downstream applications, e.g., video-text retrieval and video question answering. Existing methods either utilize multi-modal information in video-text pairs or…
With the explosive growth of video data in various complex scenarios, quickly retrieving group activities has become an urgent problem. However, many tasks can only retrieve videos focusing on an entire video, not the activity granularity.…
Image stitching synthesizes images captured from multiple perspectives into a single image with a broader field of view. The significant variations in object depth often lead to large parallax, resulting in ghosting and misalignment in the…
360{\deg} video provides an immersive experience for viewers, allowing them to freely explore the world by turning their head. However, creating high-quality 360{\deg} video content can be challenging, as viewers may miss important events…
Understanding semantic intricacies and high-level concepts is essential in image sketch generation, and this challenge becomes even more formidable when applied to the domain of videos. To address this, we propose a novel optimization-based…
We present StableMotion, a novel framework leverages knowledge (geometry and content priors) from pretrained large-scale image diffusion models to perform motion estimation, solving single-image-based image rectification tasks such as…
Understanding the structure of complex activities in untrimmed videos is a challenging task in the area of action recognition. One problem here is that this task usually requires a large amount of hand-annotated minute- or even hour-long…
Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing…