Related papers: SRFlow: A Dataset and Regularization Model for Hig…
The optical flow of humans is well known to be useful for the analysis of human action. Given this, we devise an optical flow algorithm specifically for human motion and show that it is superior to generic flow methods. Designing a method…
Research on differentiable scene representations is consistently moving towards more efficient, real-time models. Recently, this has led to the popularization of splatting methods, which eschew the traditional ray-based rendering of…
Dense 3D facial motion capture from only monocular in-the-wild pairs of RGB images is a highly challenging problem with numerous applications, ranging from facial expression recognition to facial reenactment. In this work, we propose…
Tabular regression is a well-studied problem with numerous industrial applications, yet most existing approaches focus on point estimation, often leading to overconfident predictions. This issue is particularly critical in industrial…
Obtaining the ground truth labels from a video is challenging since the manual annotation of pixel-wise flow labels is prohibitively expensive and laborious. Besides, existing approaches try to adapt the trained model on synthetic datasets…
Facial expression recognition (FER) systems in low-resolution settings face significant challenges in accurately identifying expressions due to the loss of fine-grained facial details. This limitation is especially problematic for…
The point spread function (PSF) serves as a fundamental descriptor linking the real-world scene to the captured signal, manifesting as camera blur. Accurate PSF estimation is crucial for both optical characterization and computational…
Generative modelling has been a topic at the forefront of machine learning research for a substantial amount of time. With the recent success in the field of machine learning, especially in deep learning, there has been an increased…
Facial micro-expressions are subtle and involuntary expressions that can reveal concealed emotions. Micro-expressions are an invaluable source of information in application domains such as lie detection, mental health, sentiment analysis…
We present two novel generative geometric deep learning frameworks, termed Flow Matching PointNet and Diffusion PointNet, for predicting fluid flow variables on irregular geometries by incorporating PointNet into flow matching and diffusion…
Scene flow estimation is a long-standing problem in computer vision, where the goal is to find the 3D motion of a scene from its consecutive observations. Recently, there have been efforts to compute the scene flow from 3D point clouds. A…
We introduce a novel motion estimation method, MaskFlow, that is capable of estimating accurate motion fields, even in very challenging cases with small objects, large displacements and drastic appearance changes. In addition to lower-level…
Conventional physically based rendering (PBR) pipelines generate photorealistic images through computationally intensive light transport simulations. Although recent deep learning approaches leverage diffusion model priors with geometry…
We propose to incorporate feature correlation and sequential processing into dense optical flow estimation from event cameras. Modern frame-based optical flow methods heavily rely on matching costs computed from feature correlation. In…
Despite significant progress in deep learning-based optical flow methods, accurately estimating large displacements and repetitive patterns remains a challenge. The limitations of local features and similarity search patterns used in these…
How to properly model the inter-frame relation within the video sequence is an important but unsolved challenge for video restoration (VR). In this work, we propose an unsupervised flow-aligned sequence-to-sequence model (S2SVR) to address…
Modern optical flow methods make use of salient scene feature points detected and matched within the scene as a basis for sparse-to-dense optical flow estimation. Current feature detectors however either give sparse, non uniform point…
Remote sensing images (RSIs) in real scenes may be disturbed by multiple factors such as optical blur, undersampling, and additional noise, resulting in complex and diverse degradation models. At present, the mainstream SR algorithms only…
Large-scale numerical simulations are capable of generating data up to terabytes or even petabytes. As a promising method of data reduction, super-resolution (SR) has been widely studied in the scientific visualization community. However,…
Navigating in the latent space of StyleGAN has shown effectiveness for face editing. However, the resulting methods usually encounter challenges in complicated navigation due to the entanglement among different attributes in the latent…