Skip to search formSkip to main contentSkip to account menu

Global contrast based salient region detection

This work proposes a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence, and consistently outperformed existing saliency detection methods.
View on IEEE (opens in a new tab)

Traffic-Sign Detection and Classification in the Wild

A large traffic-sign benchmark from 100000 Tencent Street View panoramas is created, going beyond previous benchmarks, and it is demonstrated how a robust end-to-end convolutional neural network (CNN) can simultaneously detect and classify trafficsigns.
View on IEEE (opens in a new tab)

PCT: Point cloud transformer

A novel framework based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing, is presented, which is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning.
View on Springer (opens in a new tab)

Morphing and Sampling Network for Dense Point Cloud Completion

This work proposes a novel approach to complete the partial point cloud in two stages, which outperforms the existing methods in both the Earth Mover's Distance (EMD) and the Chamfer Distance (CD).
View PDF on arXiv (opens in a new tab)

Deep Online Video Stabilization With Multi-Grid Warping Transformation Learning

This paper presents a video stabilization technique using a convolutional neural network that does not explicitly represent the camera path and does not use future frames, and is able to handle low-quality videos, such as night-scene videos, watermarked videos, blurry videos, and noisy videos.
View on IEEE (opens in a new tab)

SalientShape: group saliency in image collections

This work introduces group saliency to achieve superior unsupervised salient object segmentation by extracting salient objects (in collections of pre-filtered images) that maximize between-image similarities and within-image distinctness.
View on Springer (opens in a new tab)

Pose2Seg: Detection Free Human Instance Segmentation

This paper introduces a new benchmark "Occluded Human (OCHuman)", which focuses on occluded humans with comprehensive annotations including bounding-box, human pose and instance masks, and demonstrates that this pose-based framework can achieve better accuracy than the state-of-art detection-based approach on the human instance segmentation problem, and can moreover better handle occlusion.
View on IEEE (opens in a new tab)

Sketch2Photo: internet image montage

A system that composes a realistic picture from a simple freehand sketch annotated with text labels, able to automatically select suitable photographs to generate a high quality composition, using a filtering scheme to exclude undesirable images.
View on ACM (opens in a new tab)

A Shape‐Preserving Approach to Image Resizing

A novel image resizing method which attempts to ensure that important local regions undergo a geometric similarity transformation, and at the same time, to preserve image edge structure, and is efficient, and offers a closed form solution.
View on Wiley (opens in a new tab)

Geometry and Convergence Analysis of Algorithms for Registration of 3D Shapes

This work provides a convergence analysis for widely used registration algorithms such as ICP, using either closest points or tangent planes at closest points and for a recently developed approach based on quadratic approximants of the squared distance function.
View on Springer (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)