Related papers: RMFAT: Recurrent Multi-scale Feature Atmospheric T…
Image diffusion models have been adapted for real-world video super-resolution to tackle over-smoothing issues in GAN-based methods. However, these models struggle to maintain temporal consistency, as they are trained on static images,…
Video compression aims to maximize reconstruction quality with minimal bitrates. Beyond standard distortion metrics, perceptual quality and temporal consistency are also critical. However, at ultra-low bitrates, traditional end-to-end…
Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current predictive models, which lead to image distortion and…
Heat-induced air turbulence produces complex, depth-dependent image distortions that are challenging to reproduce interactively because thermally driven flow must be coupled with refractive light transport. Existing real-time methods often…
Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient…
We investigate the reconstruction of the transmission matrix of a time-evolving atmospheric channel with an online recursive optimization routine, using wave-optics simulations. We demonstrate that this estimation technique is able to keep…
We recently developed a new approach to get a stabilized image from a sequence of frames acquired through atmospheric turbulence. The goal of this algorihtm is to remove the geometric distortions due by the atmosphere movements. This method…
The temporal relationships between frames and their influences on video quality assessment (VQA) are still under-studied in existing works. These relationships lead to two important types of effects for video quality. Firstly, some temporal…
As a widely studied task, video restoration aims to enhance the quality of the videos with multiple potential degradations, such as noises, blurs and compression artifacts. Among video restorations, compressed video quality enhancement and…
Recent advances in text-to-video diffusion models have enabled high-quality video synthesis, but controllable generation remains challenging, particularly under limited data and compute. Existing fine-tuning methods for conditional…
4D millimeter-wave (mmWave) radar has been widely adopted in autonomous driving and robot perception due to its low cost and all-weather robustness. However, point-cloud-based radar representations suffer from information loss due to…
Phase referencing is a standard calibration procedure in radio interferometry. It allows to detect weak sources by using quasi-simultaneous observations of closeby sources acting as calibrators. Therefore, it is assumed that, for each…
This paper presents a complete hardware and software pipeline for real-time speech enhancement in noisy and reverberant conditions. The device consists of a microphone array and a camera mounted on eyeglasses, connected to an embedded…
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without…
The quadratic complexity of self-attention mechanism presents a significant impediment to applying Transformer models to long sequences. This work explores computational principles derived from astrocytes-glial cells critical for biological…
Video deblurring aims to enhance the quality of restored results in motion-blurred videos by effectively gathering information from adjacent video frames to compensate for the insufficient data in a single blurred frame. However, when faced…
Learned video compression (LVC) has witnessed remarkable advancements in recent years. Similar as the traditional video coding, LVC inherits motion estimation/compensation, residual coding and other modules, all of which are implemented…
Generative models are capable to address difficult problems with non-unique solutions like bandwidth extension and gap filling, removing highly non-linear artifacts from codecs, clipping and distortion, as opposed to removing linear…
3D human reconstruction from RGB images achieves decent results in good weather conditions but degrades dramatically in rough weather. Complementary, mmWave radars have been employed to reconstruct 3D human joints and meshes in rough…
Diffusion transformers enable flexible generative modeling for video. However, it is still technically challenging and computationally expensive to generate high-resolution videos with rich semantics and complex motion. Similar to…