Search Results for author:
Found 62 papers, 22 papers with code
Nighttime Defogging Using High-Low Frequency Decomposition and Grayscale-Color Networks
Given an RGB foggy nighttime image, our grayscale module takes the grayscale version of the image as input, and decomposes it into high and low frequency layers.
Object Tracking using Spatio-Temporal Networks for Future Prediction Location
To facilitate the future prediction ability, we follow three key observations: 1) object motion trajectory is affected significantly by camera motion; 2) the past trajectory of an object can act as a salient cue to estimate the object motion in the spatial domain; 3) previous frames contain the surroundings and appearance of the target object, which is useful for predicting the target object’s future locations.
uMedSum: A Unified Framework for Advancing Medical Abstractive Summarization
Current methods often sacrifice key information for faithfulness or introduce confabulations when prioritizing informativeness.
SSNeRF: Sparse View Semi-supervised Neural Radiance Fields with Augmentation
To address these artifacts and enhance robustness, we propose SSNeRF, a sparse view semi supervised NeRF method based on a teacher student framework.
Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions
Our primary novelty lies in leveraging two complementary-teacher networks to generate more reliable pseudo labels, enabling our model achieves competitive performance on extremely low-light images without the need for training with low-light ground truths.
Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models
Specifically, inspired by the recent success of large language models (LLMs) in text generation and evaluation, we adopt strong LLMs as both the data generator and gold evaluator.
CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection
We propose Class-Aware Teacher (CAT) to address the class bias issue in the domain adaptation setting.
NightHaze: Nighttime Image Dehazing via Self-Prior Learning
By increasing the noise values to approach as high as the pixel intensity values of the glow and light effect blended images, our augmentation becomes severe, resulting in stronger priors.
Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention
They struggle to acquire new knowledge while also retaining previously learned knowledge. To address these problems, we propose a semantic segmentation method for multiple adverse weather conditions that incorporates adaptive knowledge acquisition, pseudolabel blending, and weather composition replay.
NightCC: Nighttime Color Constancy via Adaptive Channel Masking
To specifically address the unique lighting conditions of nighttime and ensure the robustness of pseudo labels we propose adaptive channel masking and light uncertainty.
HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping
Further, to ensure the distinguishability among various regions, we introduce a region-level contrastive clustering loss to pull closer similar regions across images.
Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOI
In our proposed method, we introduce novel label-uncertain query augmentation techniques to enhance the diversity of the query inputs, aiming to distinguish the positive HOI class from the negative ones.
ORTexME: Occlusion-Robust Human Shape and Pose via Temporal Average Texture and Mesh Encoding
In 3D human shape and pose estimation from a monocular video, models trained with limited labeled data cannot generalize well to videos with occlusion, which is common in the wild videos.
Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction
To work with auxiliary tasks, we propose a novel auxiliary-adapted transformer, which can handle incomplete, corrupted motion data and achieve coordinate recovery via capturing spatial-temporal dependencies.
Ranked #4 on
Human Pose Forecasting
on Human3.6M
Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution
In this paper, we enhance the visibility from a single nighttime haze image by suppressing glow and enhancing low-light regions.
Dynamic Transformers Provide a False Sense of Efficiency
Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference.
DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment
Thanks to the proposed fusion module, our method is robust not only to occlusion and large pitch and roll view angles, which is the benefit of our image space approach, but also to noise and large yaw angles, which is the benefit of our model space method.
Ranked #1 on
3D Face Reconstruction
on AFLW2000-3D
(Mean NME metric)
Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert
To address the problem, we propose using a lip-reading expert to improve the intelligibility of the generated lip regions by penalizing the incorrect generation results.
2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection
Object detection at night is a challenging problem due to the absence of night image annotations.
EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning
In motion prediction tasks, maintaining motion equivariance under Euclidean geometric transformations and invariance of agent interaction is a critical and fundamental principle.
Ranked #1 on
Human Pose Forecasting
on HARPER
Deep Homography Mixture for Single Image Rolling Shutter Correction
In this work, we adopt a more straightforward method to learn deep homography mixture motion between an RS image and its corresponding GS image, without large solution space or strict restrictions on image features.
Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning
To further enforce the reflectance layer to be independent of shadows and specularities in the second-stage refinement, we introduce an S-Aware network that distinguishes the reflectance image from the input image.
Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation
In our DA framework, we retain the depth and background information during the domain feature alignment.
MIMT: Multi-Illuminant Color Constancy via Multi-Task Local Surface and Light Color Learning
To have better cues of the local surface/light colors under multiple light color conditions, we design a novel multi-task learning framework.
Uncertainty-aware Gait Recognition via Learning from Dirichlet Distribution-based Evidence
Existing gait recognition frameworks retrieve an identity in the gallery based on the distance between a probe sample and the identities in the gallery.
DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity
Most existing methods rely on binary shadow masks, without considering the ambiguous boundaries of soft and self shadows.
Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal
Few existing image defogging or dehazing methods consider dense and non-uniform particle distributions, which usually happen in smoke, dust and fog.
Ranked #2 on
Nonhomogeneous Image Dehazing
on NH-HAZE validation
Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons
In multi-person 2D pose estimation, the bottom-up methods simultaneously predict poses for all persons, and unlike the top-down methods, do not rely on human detection.
DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network
To address the problem, in this paper, we propose an unsupervised domain-classifier guided shadow removal network, DC-ShadowNet.
Ranked #4 on
Shadow Removal
on SRD
Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression
To address this problem, we need to suppress the light effects in bright regions while, at the same time, boosting the intensity of dark regions.
Ranked #26 on
Low-Light Image Enhancement
on LOL
Feature-Aligned Video Raindrop Removal with Temporal Constraints
Our single image module employs a raindrop removal network to generate initial raindrop removal results, and create a mask representing the differences between the input and initial output.
Dual networks based 3D Multi-Person Pose Estimation from Monocular Video
Most of the methods focus on single persons, which estimate the poses in the person-centric coordinates, i. e., the coordinates based on the center of the target person.
Ranked #1 on
3D Human Pose Estimation
on JTA
3D Multi-Person Pose Estimation (absolute)
3D Multi-Person Pose Estimation (root-relative)
+4
Nighttime Visibility Enhancement by Increasing the Dynamic Range and Suppression of Light Effects
In this paper, given a single nighttime image as input, our goal is to enhance its visibility by increasing the dynamic range of the intensity, and thus can boost the intensity of the low light regions, and at the same time, suppress the light effects (glow, glare) simultaneously.
Self-Aligned Video Deraining With Transmission-Depth Consistency
In this paper, we address the problems of rain streaks and rain accumulation removal in video, by developing a self-aligned network with transmission-depth consistency.
Human Object Interaction Detection using Two-Direction Spatial Enhancement and Exclusive Object Prior
At inference, we propose a human-object regrouping approach by considering the object-exclusive property of an action, where the target object should not be shared by more than one human.
Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks
Besides the integration of top-down and bottom-up networks, unlike existing pose discriminators that are designed solely for single person, and consequently cannot assess natural inter-person interactions, we propose a two-person pose discriminator that enforces natural two-person interactions.
3D Multi-Person Pose Estimation (absolute)
3D Multi-Person Pose Estimation (root-relative)
+2
Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos
To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not require camera parameters.
Ranked #1 on
Root Joint Localization
on Human3.6M
3D Absolute Human Pose Estimation
3D Multi-Person Pose Estimation (absolute)
+5
Object Tracking Using Spatio-Temporal Future Prediction
Our trajectory prediction module predicts the target object's locations in the current and future frames based on the object's past trajectory.
Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization
Addressing these problems, we introduce a spatio-temporal network for robust 3D human pose estimation.
Estimation of Camera Response Function using Prediction Consistency and Gradual Refinement with an Extension to Deep Learning
Second, we employ a gradual refinement scheme in which we start from a simple CRF model to generate a result which is more robust to noise but less accurate, and then we gradually increase the model's complexity to improve the result.
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training
Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in recent years.
Ranked #3 on
3D Human Pose Estimation
on HumanEva-I
Optical Flow in Dense Foggy Scenes using Semi-Supervised Learning
Initially, given a pair of synthetic fog images, its corresponding clean images and optical flow ground-truths, in one training batch we train our network in a supervised manner.
Single Image Deraining: From Model-Based to Data-Driven and Beyond
The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation.
Nighttime Stereo Depth Estimation using Joint Translation-Stereo Learning: Light Effects and Uninformative Regions
To address the problem, we introduce a network joining day/night translation and stereo.
Hyperspectral City V1.0 Dataset and Benchmark
This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark.
GraphX$^{NET}-$ Chest X-Ray Classification Under Extreme Minimal Supervision
The task of classifying X-ray data is a problem of both theoretical and clinical interest.
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning
This filtering is guided by a rain-free residue image --- its content is used to set the passbands for the two channels in a spatially-variant manner so that the background details do not get mixed up with the rain-streaks.
Certainty Driven Consistency Loss on Multi-Teacher Networks for Semi-Supervised Learning
Specifically, we propose two approaches, i. e. Filtering CCL and Temperature CCL to either filter out uncertain predictions or pay less attention on them in the consistency regularization.
Loss Guided Activation for Action Recognition in Still Images
This requirement of bounding boxes as part of the input is needed to enable the methods to ignore irrelevant contexts and extract only human features.
Robust Optical Flow in Rainy Scenes
Optical flow estimation in rainy scenes is challenging due to degradation caused by rain streaks and rain accumulation, where the latter refers to the poor visibility of remote scenes due to intense rainfall.
Single Image Deraining using Scale-Aware Multi-Stage Recurrent Network
Given a single input rainy image, our goal is to visually remove rain streaks and the veiling effect caused by scattering and transmission of rain streaks and rain droplets.
Attentive Generative Adversarial Network for Raindrop Removal from a Single Image
This injection of visual attention to both generative and discriminative networks is the main contribution of this paper.
Robust Optical Flow Estimation in Rainy Scenes
To handle rain accumulation, our method decomposes the image into a piecewise-smooth background layer and a high-frequency detail layer.
Deep Joint Rain Detection and Removal from a Single Image
Based on the first model, we develop a multi-task deep learning architecture that learns the binary rain streak map, the appearance of rain streaks, and the clean background, which is our ultimate output.
Haze Visibility Enhancement: A Survey and Quantitative Benchmarking
This paper provides a comprehensive survey of methods dealing with visibility enhancement of images taken in hazy or foggy scenes.
Rain Streak Removal Using Layer Priors
This paper addresses the problem of rain streak removal from a single image.
Robust Optical Flow Estimation of Double-Layer Images under Transparency or Reflection
This paper deals with a challenging, frequently encountered, yet not properly investigated problem in two-frame optical flow estimation.
Waterdrop Stereo
(2) The imagery inside a water-drop is determined by the water-drop 3D shape and total reflection at the boundary.
Nighttime Haze Removal With Glow and Multiple Light Colors
We demonstrate the effectiveness of our nighttime haze model and correction method on a number of examples and compare our results with existing daytime and nighttime dehazing methods' results.
Water Detection through Spatio-Temporal Invariant Descriptors
Experimental evaluation on the Video Water Database and the DynTex database indicates the effectiveness of the proposed algorithm, outperforming multiple algorithms for dynamic texture recognition and material recognition by ca.
Simultaneous Video Defogging and Stereo Reconstruction
We present a method to jointly estimate scene depth and recover the clear latent image from a foggy video sequence.
Adherent Raindrop Detection and Removal in Video
First, it detects raindrops based on the motion and the intensity temporal derivatives of the input video.
