Related papers: PDC-Net+: Enhanced Probabilistic Dense Corresponde…

Autoregressive next-step prediction models have become the de-facto standard for building data-driven neural solvers to forecast time-dependent partial differential equations (PDEs). Denoise training that is closely related to diffusion…

Multi-view depth estimation plays a critical role in reconstructing and understanding the 3D world. Recent learning-based methods have made significant progress in it. However, multi-view depth estimation is fundamentally a…

This paper proposes a DNN-based system that detects multiple people from a single depth image. Our neural network processes a depth image and outputs a likelihood map in image coordinates, where each detection corresponds to a…

We propose a robust alignment technique for Standard Fundus Images (SFIs) and Ultra-Widefield Fundus Images (UWFIs), which are challenging to align due to differences in scale, appearance, and the scarcity of distinctive features. Our…

Training a deep neural network is a non-trivial task. Not only the tuning of hyperparameters, but also the gathering and selection of training data, the design of the loss function, and the construction of training schedules is important to…

Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained…

In the last few years, convolutional neural networks (CNNs) have demonstrated increasing success at learning many computer vision tasks including dense estimation problems such as optical flow and stereo matching. However, the joint…

Diffusion models have become a successful approach for solving various image inverse problems by providing a powerful diffusion prior. Many studies tried to combine the measurement into diffusion by score function replacement, matrix…

In this work we use deep learning to establish dense correspondences between a 3D object model and an image "in the wild". We introduce "DenseReg", a fully-convolutional neural network (F-CNN) that densely regresses at every foreground…

A novel, non-learning-based, saliency-aware, shape-cognizant correspondence determination technique is proposed for matching image pairs that are significantly disparate in nature. Images in the real world often exhibit high degrees of…

Template matching by normalized cross correlation (NCC) is widely used for finding image correspondences. We improve the robustness of this algorithm by preprocessing images with "siamese" convolutional networks trained to maximize the…

Our work proposes a novel deep learning framework for estimating crowd density from static images of highly dense crowds. We use a combination of deep and shallow, fully convolutional networks to predict the density map for a given crowd…

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…

Recently, regression-based methods have dominated the field of 3D human pose and shape estimation. Despite their promising results, a common issue is the misalignment between predictions and image observations, often caused by minor joint…

Existing unsupervised image alignment methods exhibit limited accuracy and high computational complexity. To address these challenges, we propose a dense cross-scale image alignment model. It takes into account the correlations between…

3D human pose estimation has wide applications in fields such as intelligent surveillance, motion capture, and virtual reality. However, in real-world scenarios, issues such as occlusion, noise interference, and missing viewpoints can…

3D pose estimation from a single 2D image is an important and challenging task in computer vision with applications in autonomous driving, robot manipulation and augmented reality. Since 3D pose is a continuous quantity, a natural…

Image prediction methods often struggle on tasks that require changing the positions of objects, such as video prediction, producing blurry images that average over the many positions that objects might occupy. In this paper, we propose a…

This paper focuses on the task of 4D shape reconstruction from a sequence of point clouds. Despite the recent success achieved by extending deep implicit representations into 4D space, it is still a great challenge in two respects, i.e. how…

A key technical challenge in performing 6D object pose estimation from RGB-D image is to fully leverage the two complementary data sources. Prior works either extract information from the RGB image and depth separately or use costly…