Related papers: Stitching Stabilizer: Two-frame-stitching Video St…
One of the core components of conventional (i.e., non-learned) video codecs consists of predicting a frame from a previously-decoded frame, by leveraging temporal correlations. In this paper, we propose an end-to-end learned system for…
With the emergence of diffusion models and rapid development in image processing, it has become effortless to generate fancy images in tasks such as style transfer and image editing. However, these impressive image processing approaches…
Recently, transformer-based methods have gained significant success in sequential 2D-to-3D lifting human pose estimation. As a pioneering work, PoseFormer captures spatial relations of human joints in each video frame and human dynamics…
Existing methods of 3D dense face alignment mainly concentrate on accuracy, thus limiting the scope of their practical applications. In this paper, we propose a novel regression framework named 3DDFA-V2 which makes a balance among speed,…
Focus stacking is widely used in micro, macro, and landscape photography to reconstruct all-in-focus images from multiple frames obtained with focus bracketing, that is, with shallow depth of field and different focus planes. Existing deep…
We introduce a compressive single-pixel imaging (SPI) framework for high-resolution image capture in fractions of a second. This framework combines a dedicated sampling strategy with a tailored reconstruction method to enable high-quality…
This work introduces a novel end-to-end approach for estimating extrinsic parameters of cameras in multi-camera setups on real-life sports fields. We identify the source of significant calibration errors in multi-camera environments and…
Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window. They are less efficient compared to the recurrent-based methods. In this work, we propose a novel…
Video Snapshot Compressive Imaging (SCI) aims to use a low-speed 2D camera to capture high-speed scene as snapshot compressed measurements, followed by a reconstruction algorithm to reconstruct the high-speed video frames. State-of-the-art…
Several approaches to image stitching use different constraints to estimate the motion model between image pairs. These constraints can be roughly divided into two categories: geometric constraints and photometric constraints. In this…
Multi-camera systems are widely employed in sports to capture the 3D motion of athletes and equipment, yet calibrating their extrinsic parameters remains costly and labor-intensive. We introduce an efficient, tool-free method for…
This work proposes a new method for real-time dense 3d reconstruction for common 360{\deg} action cams, which can be mounted on small scouting UAVs during USAR missions. The proposed method extends a feature based Visual monocular SLAM…
Dual-fisheye lens cameras have been increasingly used for 360-degree immersive imaging. However, the limited overlapping field of views and misalignment between the two lenses give rise to visible discontinuities in the stitching…
Accurate estimation of stereo camera extrinsic parameters is the key to guarantee the performance of stereo matching algorithms. In prior arts, the online self-calibration of stereo cameras has commonly been formulated as a specialized…
Spike cameras, as innovative neuromorphic devices, generate continuous spike streams to capture high-speed scenes with lower bandwidth and higher dynamic range than traditional RGB cameras. However, reconstructing high-quality images from…
Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality images. Current…
In order to provide a cloud service of optical quantum computing, it is inevitable to stabilize the optical system for many hours. It is advantageous to construct a fiber-based system, which does not require spatial alignment. However,…
Image stitching aims at stitching the images taken from different viewpoints into an image with a wider field of view. Existing methods warp the target image to the reference image using the estimated warp function, and a homography is one…
We present an inverse image-formation module that can enhance the robustness of existing visual SLAM pipelines for casually captured scenarios. Casual video captures often suffer from motion blur and varying appearances, which degrade the…
Recognizing various surgical tools, actions and phases from surgery videos is an important problem in computer vision with exciting clinical applications. Existing deep-learning-based methods for this problem either process each surgical…