Related papers: CRAFT: Cross-Attentional Flow Transformer for Robu…
Video frame interpolation has been actively studied with the development of convolutional neural networks. However, due to the intrinsic limitations of kernel weight sharing in convolution, the interpolated frame generated by it may lose…
This paper presents a novel method for detecting scene changes from a pair of images with a difference of camera viewpoints using a dense optical flow based change detection network. In the case that camera poses of input images are fixed…
This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. In the context of dense matching, many works benefit from one of two forms of aggregation: feature aggregation,…
We present a new 3D point-based detector model, named Shift-SSD, for precise 3D object detection in autonomous driving. Traditional point-based 3D object detectors often employ architectures that rely on a progressive downsampling of…
Optical flow computation is essential in the early stages of the video processing pipeline. This paper focuses on a less explored problem in this area, the 360$^\circ$ optical flow estimation using deep neural networks to support…
Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…
Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ…
Current image compression models often require separate models for each quality level, making them resource-intensive in terms of both training and storage. To address these limitations, we propose an innovative approach that utilizes…
Forecasting traffic flows is a central task in intelligent transportation system management. Graph structures have shown promise as a modeling framework, with recent advances in spatio-temporal modeling via graph convolution neural…
Pre-trained diffusion models are commonly used to generate clean data (e.g., images) from random noises, effectively forming pairs of noises and corresponding clean images. Distillation on these pre-trained models can be viewed as the…
Motion is a dominant cue in automated driving systems. Optical flow is typically computed to detect moving objects and to estimate depth using triangulation. In this paper, our motivation is to leverage the existing dense optical flow to…
It is hard to densely track a nonrigid object in long term, which is a fundamental research issue in the computer vision community. This task often relies on estimating pairwise correspondences between images over time where the error is…
Semantic correspondence is the problem of establishing correspondences across images depicting different instances of the same object or scene class. One of recent approaches to this problem is to estimate parameters of a global…
In advanced paradigms of autonomous driving, learning Bird's Eye View (BEV) representation from surrounding views is crucial for multi-task framework. However, existing methods based on depth estimation or camera-driven attention are not…
In recent years, powered by the learned discriminative representation via graph neural network (GNN) models, deep graph matching methods have made great progresses in the task of matching semantic features. However, these methods usually…
This paper presents a novel architecture for simultaneous estimation of highly accurate optical flows and rigid scene transformations for difficult scenarios where the brightness assumption is violated by strong shading changes. In the case…
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…
Multimodal visual information fusion aims to integrate the multi-sensor data into a single image which contains more complementary information and less redundant features. However the complementary information is hard to extract, especially…
Although face recognition (FR) has achieved great success in recent years, it is still challenging to accurately recognize faces in low-quality images due to the obscured facial details. Nevertheless, it is often feasible to make…
One-shot object detection aims at detecting novel objects according to merely one given instance. With extreme data scarcity, current approaches explore various feature fusions to obtain directly transferable meta-knowledge. Yet, their…