Search Results for author:
Found 58 papers, 23 papers with code
PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click
We propose to employ phrase expressions as another interaction input to infer the attributes of target object.
IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation
Generative object compositing emerges as a promising new avenue for compositional image editing.
SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis
On the highly competitive ADE20K and COCO benchmarks, our data generation method markedly improves the performance of state-of-the-art segmentation models in semantic segmentation, panoptic segmentation, and instance segmentation.
Putting the Object Back into Video Object Segmentation
We present Cutie, a video object segmentation (VOS) network with object-level memory reading, which puts the object representation from memory back into the video object segmentation result.
Ranked #1 on
Semi-Supervised Video Object Segmentation
on MOSE
Tracking Anything with Decoupled Video Segmentation
To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation.
Ranked #1 on
Unsupervised Video Object Segmentation
on DAVIS 2016 val
(using extra training data)
Open-Vocabulary Video Segmentation
Open-World Video Segmentation
+7
Interactive Segmentation for Diverse Gesture Types Without Context
Interactive segmentation entails a human marking an image to guide how a model either creates or edits a segmentation.
Towards Open-World Segmentation of Parts
Second, we introduce a novel approach to improve part segmentation on unseen objects, inspired by an interesting finding -- for unseen objects, the pixel-wise features extracted by the model often reveal high-quality part segments.
GamutMLP: A Lightweight MLP for Color Loss Recovery
Inspired by neural implicit representations for 2D images, we propose a method that optimizes a lightweight multi-layer-perceptron (MLP) model during the gamut reduction step to predict the clipped values.
Improving Diffusion Models for Scene Text Editing with Dual Encoders
Scene text editing is a challenging task that involves modifying or inserting specified texts in an image while maintaining its natural and realistic appearance.
ObjectStitch: Object Compositing With Diffusion Model
Object compositing based on 2D images is a challenging problem since it typically involves multiple processing stages such as color harmonization, geometry correction and shadow generation to generate realistic results.
ObjectStitch: Generative Object Compositing
Object compositing based on 2D images is a challenging problem since it typically involves multiple processing stages such as color harmonization, geometry correction and shadow generation to generate realistic results.
One-Trimap Video Matting
A key of OTVM is the joint modeling of trimap propagation and alpha prediction.
Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation
Deep image matting methods have achieved increasingly better results on benchmarks (e. g., Composition-1k/alphamatting. com).
Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks
Recently, feature backpropagating refinement scheme (f-BRS) has been proposed for the task of interactive segmentation, which enables efficient optimization of a small set of auxiliary variables inserted into the pretrained network to produce object segmentation that better aligns with user inputs.
Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning
Generalized few-shot semantic segmentation was introduced to move beyond only evaluating few-shot segmentation models on novel classes to include testing their ability to remember base classes.
Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach
We also introduce Text Refinement Network (TexRNet), a novel text segmentation approach that adapts to the unique properties of text, e. g. non-convex boundary, diverse texture, etc., which often impose burdens on traditional segmentation models.
Text and Style Conditioned GAN for Generation of Offline Handwriting Lines
This paper presents a GAN for generating images of handwritten lines conditioned on arbitrary text and latent style vectors.
Objectness-Aware Few-Shot Semantic Segmentation
We demonstrate how to increase overall model capacity to achieve improved performance, by introducing objectness, which is class-agnostic and so not prone to overfitting, for complementary use with class-specific features.
DeepStrip: High Resolution Boundary Refinement
In this paper, we target refining the boundaries in high resolution images given low resolution masks.
Getting to 99% Accuracy in Interactive Segmentation
We propose a novel interactive architecture and a novel training scheme that are both tailored to better exploit the user workflow.
Deep Visual Template-Free Form Parsing
Automatic, template-free extraction of information from form images is challenging due to the variety of form layouts.
Unconstrained Foreground Object Search
Many people search for foreground objects to use when editing images.
Answering Questions about Data Visualizations using Efficient Bimodal Fusion
Chart question answering (CQA) is a newly proposed visual question answering (VQA) task where an algorithm must answer questions about data visualizations, e. g. bar charts, pie charts, and line graphs.
Image Recoloring Based on Object Color Distributions
We present a method to perform automatic image recoloring based on the distribution of colors associated with objects present in an image.
Measuring Human Perception to Improve Handwritten Document Transcription
The subtleties of human perception, as measured by vision scientists through the use of psychophysics, are important clues to the internal workings of visual recognition.
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i. e., even the largest video segmentation dataset only contains 90 short video clips.
Ranked #12 on
Video Object Segmentation
on YouTube-VOS 2018
(F-Measure (Unseen) metric)
Compositing-aware Image Search
We present a new image search technique that, given a background image, returns compatible foreground objects for image compositing tasks.
Interactive Boundary Prediction for Object Selection
Instead of relying on pre-defined low-level image features, our method adaptively predicts object boundaries according to image content and user interactions.
Start, Follow, Read: End-to-End Full-Page Handwriting Recognition
Despite decades of research, offline handwriting recognition (HWR) of degraded historical documents remains a challenging problem, which if solved could greatly improve the searchability of online cultural heritage archives.
Ranked #12 on
Handwritten Text Recognition
on IAM
Disentangling Structure and Aesthetics for Style-Aware Image Completion
Content-aware image completion or in-painting is a fundamental tool for the correction of defects or removal of objects in images.
Guided Image Inpainting: Replacing an Image Region by Pulling Content from Another Image
Deep generative models have shown success in automatically synthesizing missing image regions using surrounding context.
Discriminability objective for training descriptive captions
One property that remains lacking in image captions generated by contemporary methods is discriminability: being able to tell two images apart given the caption for one of them.
DVQA: Understanding Data Visualizations via Question Answering
Bar charts are an effective way to convey numeric information, but today's algorithms cannot parse them.
Group-Theme Recoloring for Multi-Image Color Consistency
Methods such as color transfer are effective in making an image share similar colors with a target image; however, color transfer is not suitable for modifying multiple images.
Deep GrabCut for Object Selection
In this paper, we propose a novel segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map.
Depth From Defocus in the Wild
We consider the problem of two-frame depth from defocus in conditions unsuitable for existing methods yet typical of everyday photography: a handheld cellphone camera, a small aperture, a non-stationary scene and sparse surface texture.
Forecasting Human Dynamics from Static Images
This paper presents the first study on forecasting human dynamics from static images.
Deep Image Matting
We evaluate our algorithm on the image matting benchmark, our testing set, and a wide variety of real images.
SURGE: Surface Regularized Geometry Estimation from a Single Image
This paper introduces an approach to regularize 2. 5D surface normal and depth predictions at each pixel given a single input image.
Salient Object Subitizing
We study the problem of Salient Object Subitizing, i. e. predicting the existence and the number of salient objects in an image using holistic cues.
Two Illuminant Estimation and User Correction Preference
Existing methods attempt to estimate a spatially varying illumination map, however, results are error prone and the resulting illumination maps are too low-resolution to be used for proper spatially varying white-balance correction.
Interactive Segmentation on RGBD Images via Cue Selection
While these methods achieve better results than color-based methods, they are still limited in either using depth as an additional color channel or simply combining depth with color in a linear way.
Unconstrained Salient Object Detection via Proposal Subset Optimization
Our system leverages a Convolutional-Neural-Network model to generate location proposals of salient objects.
Automatic Annotation of Structured Facts in Images
Motivated by the application of fact-level image understanding, we present an automatic method for data collection of structured visual facts from images with captions.
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network.
Deep Interactive Object Selection
Interactive object selection is a very important research problem and has many applications.
Ranked #11 on
Interactive Segmentation
on SBD
Minimum Barrier Salient Object Detection at 80 FPS
Powered by this fast MBD transform algorithm, the proposed salient object detection method runs at 80 FPS, and significantly outperforms previous methods with similar speed on four large benchmark datasets, and achieves comparable or better performance than state-of-the-art methods.
Ranked #6 on
Video Salient Object Detection
on VOS-T
(using extra training data)
Beyond White: Ground Truth Colors for Color Constancy Correction
A limitation in color constancy research is the inability to establish ground truth colors for evaluating corrected images.
Sherlock: Scalable Fact Learning in Images
We show that learning visual facts in a structured way enables not only a uniform but also generalizable visual understanding.
LCNN: Low-level Feature Embedded CNN for Salient Object Detection
In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images.
PatchCut: Data-Driven Object Segmentation via Local Shape Transfer
The transferred local shape masks constitute a patch-level segmentation solution space and we thus develop a novel cascade algorithm, PatchCut, for coarse-to-fine object segmentation.
Effective Learning-Based Illuminant Estimation Using Simple Features
More recent state-of-the-art methods employ learning-based techniques that produce better results, but often rely on complex features and have long evaluation and training times.
Towards Unified Depth and Semantic Prediction From a Single Image
By allowing for interactions between the depth and semantic information, the joint network provides more accurate depth prediction than a state-of-the-art CNN trained solely for depth prediction [5].
Inner and Inter Label Propagation: Salient Object Detection in the Wild
For most natural images, some boundary superpixels serve as the background labels and the saliency of other superpixels are determined by ranking their similarities to the boundary labels based on an inner propagation scheme.
Joint Object and Part Segmentation using Deep Learned Potentials
Segmenting semantic objects from images and parsing them into their respective semantic parts are fundamental steps towards detailed object understanding in computer vision.
Context Driven Scene Parsing with Attention to Rare Classes
This paper presents a scalable scene parsing algorithm based on image retrieval and superpixel matching.
Semantic Object Selection
With the tag provided by the user we do a text query of an image database to gather exemplars of the object.
Improving Image Matting Using Comprehensive Sampling Sets
The first is that the range in which the foreground and background are sampled is often limited to such an extent that the true foreground and background colors are not present.
