Search Results for author:
Found 54 papers, 27 papers with code
AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting
Three-dimensional scene inpainting is crucial for applications from virtual reality to architectural visualization, yet existing methods struggle with view consistency and geometric accuracy in 360{\deg} unbounded scenes.
CorrFill: Enhancing Faithfulness in Reference-based Inpainting with Correspondence Guidance in Diffusion Models
In the task of reference-based image inpainting, an additional reference image is provided to restore a damaged target image to its original state.
ORFormer: Occlusion-Robust Transformer for Accurate Facial Landmark Detection
The messenger token aggregates features from all but its patch.
Ranking-aware adapter for text-driven image ordering with CLIP
Overall, our approach primarily focuses on ranking images with a single instruction, which provides a natural and generalized way of learning from visual differences across images, bypassing the need for extensive text prompts tailored to individual tasks.
TANet: Triplet Attention Network for All-In-One Adverse Weather Image Restoration
In this paper, we propose a Triplet Attention Network (TANet) to efficiently and effectively address all-in-one adverse weather image restoration.
Improving Visual Object Tracking through Visual Prompting
PiVOT proposes a prompt generation network with the pre-trained foundation model CLIP to automatically generate and refine visual prompts, enabling the transfer of foundation model knowledge for tracking.
Ranked #1 on
Visual Object Tracking
on AVisT
Make Graph-based Referring Expression Comprehension Great Again through Expression-guided Dynamic Gating and Regression
Extensive experimental results on the RefCOCO, RefCOCO+, RefCOCOg, Flickr30K, RefClef, and Ref-reasoning datasets demonstrate the effectiveness of the DGC module and the EGR strategy in consistently boosting the performances of various graph-based REC methods.
Domain-adaptive Video Deblurring via Test-time Blurring
Next, we utilize a blurring model to produce blurred images based on the pseudo-sharp images extracted during testing.
Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation
This paper addresses text-supervised semantic segmentation, aiming to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations.
ViStripformer: A Token-Efficient Transformer for Versatile Video Restoration
Besides, ViStripformer is an effective and efficient transformer architecture with much lower memory usage than the vanilla transformer.
ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation
Since continuous motion causes blurred artifacts during image exposure, we aspire to develop a groundbreaking blur augmentation method to generate diverse blurred images by simulating motion trajectories in a continuous space.
Ranked #3 on
Deblurring
on RealBlur-J
PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation
This paper proposes a cross-modal distillation framework, PartDistill, which transfers 2D knowledge from vision-language models (VLMs) to facilitate 3D shape part segmentation.
Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection
Semi-supervised object detection is crucial for 3D scene understanding, efficiently addressing the limitation of acquiring large-scale 3D bounding box annotations.
2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision
Considering the high annotation cost of point clouds, effective 2D and 3D feature fusion based on weakly supervised learning is in great demand.
Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction
To address this, we propose the continuous exposure value representation (CEVR), which uses an implicit function to generate LDR images with arbitrary EVs, including those unseen during training.
MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution
We motivate the use of forward motion from the perspective of learning individual motion trajectories, as opposed to learning a mixture of motion trajectories with backward motion.
Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection
In this work, we propose an object-level point augmentor (OPA) that performs local transformations for semi-supervised 3D object detection.
Meta Transferring for Deblurring
Most previous deblurring methods were built with a generic model trained on blurred images and their sharp counterparts.
Stripformer: Strip Transformer for Fast Image Deblurring
Images taken in dynamic scenes may contain unwanted motion blur, which significantly degrades visual quality.
Ranked #10 on
Deblurring
on RealBlur-R
An MIL-Derived Transformer for Weakly Supervised Point Cloud Segmentation
We address weakly supervised point cloud segmentation by proposing a new model, MIL-derived transformer, to mine additional supervisory signals.
Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing
The audio-visual video parsing task aims to temporally parse a video into audio or visual event categories.
Unsupervised Sound Localization via Iterative Contrastive Learning
Sound localization aims to find the source of the audio signal in the visual scene.
BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring
Image motion blur results from a combination of object motions and camera shakes, and such blurring effect is generally directional and non-uniform.
Ranked #12 on
Deblurring
on RealBlur-R
Unsupervised Point Cloud Object Co-Segmentation by Co-Contrastive Learning and Mutual Attention Sampling
We formulate this task as an object point sampling problem, and develop two techniques, the mutual attention module and co-contrastive learning, to enable it.
Temporal-Aware Self-Supervised Learning for 3D Hand Pose and Mesh Estimation in Videos
Experiments show that our modelachieves surprisingly good results, with 3D estimation ac-curacy on par with the state-of-the-art models trained with3D annotations, highlighting the benefit of the temporalconsistency in constraining 3D prediction models.
MVHM: A Large-Scale Multi-View Hand Mesh Benchmark for Accurate 3D Hand Pose Estimation
Based on the match algorithm, we propose an efficient pipeline to generate a large-scale multi-view hand mesh (MVHM) dataset with accurate 3D hand mesh and joint labels.
DGGAN: Depth-image Guided Generative Adversarial Networks for Disentangling RGB and Depth Images in 3D Hand Pose Estimation
Estimating3D hand poses from RGB images is essentialto a wide range of potential applications, but is challengingowing to substantial ambiguity in the inference of depth in-formation from RGB images.
MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis
Estimating the 3D hand pose from a monocular RGB image is important but challenging.
Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector
A domain adaptive object detector aims to adapt itself to unseen domains that may contain variations of object appearance, viewpoints or backgrounds.
Regularizing Meta-Learning via Gradient Dropout
With the growing attention on learning-to-learn new tasks using only a few examples, meta-learning has been widely used in numerous problems such as few-shot classification, reinforcement learning, and domain generalization.
Deep Semantic Matching with Foreground Detection and Cycle-Consistency
Establishing dense semantic correspondences between object instances remains a challenging problem due to background clutter, significant scale and pose differences, and large intra-class variations.
Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond
Person re-identification (re-ID) aims at matching images of the same person across camera views.
CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency
Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another (e. g., synthetic to real images).
Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior
This paper presents a weakly supervised instance segmentation method that consumes training data with tight bounding box annotations.
Box-supervised Instance Segmentation
Multiple Instance Learning
+4
Referring Expression Object Segmentation with Caption-Aware Consistency
To this end, we propose an end-to-end trainable comprehension network that consists of the language and visual encoders to extract feature representations from both domains.
Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification
Person re-identification (re-ID) aims at matching images of the same identity across camera views.
Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation
In contrast to existing algorithms that tackle the tasks of semantic matching and object co-segmentation in isolation, our method exploits the complementary nature of the two tasks.
Deep Video Frame Interpolation using Cyclic Frame Generation
In addition to the cycle consistency loss, we propose two extensions: motion linearity loss and edge-guided training.
Unseen Object Segmentation in Videos via Transferable Representations
The entire process is decomposed into two tasks: 1) solving a submodular function for selecting object-like segments, and 2) learning a CNN model with a transferable module for adapting seen categories in the source domain to the unseen target video.
Generating Realistic Training Images Based on Tonality-Alignment Generative Adversarial Networks for Hand Pose Estimation
Hand pose estimation from a monocular RGB image is an important but challenging task.
Learning Conditional Random Fields with Augmented Observations for Partially Observed Action Recognition
This paper aims at recognizing partially observed human actions in videos.
Unsupervised CNN-based Co-Saliency Detection with Graphical Optimization
In this paper, we address co-saliency detection in a set of images jointly covering objects of a specific class by an unsupervised convolutional neural network (CNN).
Adversarial Learning for Semi-Supervised Semantic Segmentation
We propose a method for semi-supervised semantic segmentation using an adversarial network.
DeepCD: Learning Deep Complementary Descriptors for Patch Representations
This paper presents the DeepCD framework which learns a pair of complementary descriptors jointly for a patch by employing deep learning techniques.
Deep Co-Occurrence Feature Learning for Visual Object Recognition
We tackle the three issues by introducing a new network layer, called co-occurrence layer.
Accumulated Stability Voting: A Robust Descriptor From Descriptors of Multiple Scales
Experiments on popular benchmarks demonstrate the effectiveness of our descriptors and their superiority to the state-of-the-art descriptors.
Progressive Feature Matching With Alternate Descriptor Selection and Correspondence Enrichment
We address two difficulties in establishing an accurate system for image matching.
Blur Kernel Estimation Using Normalized Color-Line Prior
The intermediate patches can then guide the estimation of the blur kernel.
Robust Image Alignment With Multiple Feature Descriptors and Matching-Guided Neighborhoods
First, the performance of descriptor-based approaches to image alignment relies on the chosen descriptor, but the optimal descriptor typically varies from image to image, or even pixel to pixel.
Descriptor Ensemble: An Unsupervised Approach to Descriptor Fusion in the Homography Space
Inspired by the observation that the homographies of correct feature correspondences vary smoothly along the spatial domain, our approach stands on the unsupervised nature of feature matching, and can select a good descriptor for matching each feature point.
Multiple Structured-Instance Learning for Semantic Segmentation with Uncertain Training Data
By treating a bounding box as a bag with its segment hypotheses as structured instances, MSIL-CRF selects the most likely segment hypotheses by leveraging the knowledge derived from both the labeled and uncertain training data.
Depth and Skeleton Associated Action Recognition without Online Accessible RGB-D Cameras
Our approach aims to enhance action recognition in RGB videos by leveraging the extra database.
Robust Feature Matching with Alternate Hough and Inverted Hough Transforms
Inspired by the fact that nearby features on the same object share coherent homographies in matching, we cast the task of feature matching as a density estimation problem in the Hough space spanned by the hypotheses of homographies.
Dimensionality Reduction for Data in Multiple Feature Representations
In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance.
