Search Results for author:
Found 74 papers, 44 papers with code
SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels
Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data.
DiffComplete: Diffusion-based Generative 3D Shape Completion
We introduce a new diffusion-based approach for shape completion on 3D range scans.
CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Exploration
This paper presents CLIPXPlore, a new framework that leverages a vision-language model to guide the exploration of the 3D shape space.
UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentation
Besides, we propose B-Seg, a building instance segmentation method to establish UrbanBIS.
You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding
3D scene understanding, e. g., point cloud semantic and instance segmentation, often requires large-scale annotated training data, but clearly, point-wise labels are too tedious to prepare.
DreamStone: Image as Stepping Stone for Text-Guided 3D Shape Generation
The core of our approach is a two-stage feature-space alignment strategy that leverages a pre-trained single-view reconstruction (SVR) model to map CLIP features to shapes: to begin with, map the CLIP image feature to the detail-rich 3D shape space of the SVR model, then map the CLIP text feature to the 3D shape space through encouraging the CLIP-consistency between rendered images and the input text.
Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation
This paper presents a new approach for 3D shape generation, inversion, and manipulation, through a direct generative modeling on a continuous implicit representation in wavelet domain.
Command-Driven Articulated Object Understanding and Manipulation
The key of Cart is to utilize the prediction of object structures to connect visual observations with user commands for effective manipulations.
H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction
First, we decouple hand mesh reconstruction into two branches, one to exploit finger-level non-occluded information and the other to exploit global hand orientation, with lightweight structures to promote real-time inference.
Video Instance Shadow Detection
First, we design SSIS-Track, a new framework to extract shadow-object associations in videos with paired tracking and without category specification; especially, we strive to maintain paired tracking even the objects/shadows are temporarily occluded for several frames.
Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection
Importantly, we formulate the lightweight plug-in S2D module and the point cloud reconstruction module in SDet to densify 3D features and train SDet to produce 3D features, following the dense 3D features in DDet.
Learning Reconstructability for Drone Aerial Path Planning
To reconstruct a new urban scene, we first build the 3D scene proxy, then rely on the predicted reconstruction quality and uncertainty measures by our network, based off of the proxy geometry, to guide the drone path planning.
Neural Wavelet-domain Diffusion for 3D Shape Generation
This paper presents a new approach for 3D shape generation, enabling direct generative modeling on a continuous implicit representation in wavelet domain.
ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation
Text-guided 3D shape generation remains challenging due to the absence of large paired text-shape data, the substantial semantic gap between these two modalities, and the structural complexity of 3D shapes.
Instance Shadow Detection with A Single-Stage Detector
This paper formulates a new problem, instance shadow detection, which aims to detect shadow instance and the associated object instance that cast each shadow in the input image.
Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution
Despite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy.
Boosting Single-Frame 3D Object Detection by Simulating Multi-Frame Point Clouds
To boost a detector for single-frame 3D object detection, we present a new approach to train it to simulate features and responses following a detector trained on multi-frame point clouds.
Boosting 3D Object Detection by Simulating Multimodality on Point Clouds
This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to simulate features and responses that follow a multi-modality (LiDAR-image) detector.
Semi-signed prioritized neural fitting for surface reconstruction from unoriented point clouds
To guide the network quickly fit the coarse shape, we propose to utilize the signed supervision in regions that are obviously outside the object and can be easily determined, resulting in our semi-signed supervision.
Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes
This paper introduces a novel framework called DTNet for 3D mesh reconstruction and generation via Disentangled Topology.
Towards Implicit Text-Guided 3D Shape Generation
In this work, we explore the challenging task of generating 3D shapes from text.
Towards Robust Part-aware Instance Segmentation for Industrial Bin Picking
Industrial bin picking is a challenging task that requires accurate and robust segmentation of individual object instances.
Point Set Self-Embedding
To achieve a learnable self-embedding scheme, we design a novel framework with two jointly-trained networks: one to encode the input point set into its self-embedded sparse point set and the other to leverage the embedded information for inverting the original point set back.
SNR-Aware Low-Light Image Enhancement
They are long-range operations for image regions of extremely low Signal-to-Noise-Ratio (SNR) and short-range operations for other regions.
TWIST: Two-Way Inter-Label Self-Training for Semi-Supervised 3D Instance Segmentation
We explore the way to alleviate the label-hungry problem in a semi-supervised setting for 3D instance segmentation.
Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
To address the high cost and challenges of 3D point-level labeling, we present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance.
Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction
3D hand-mesh reconstruction from RGB images facilitates many applications, including augmented reality (AR).
SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation
We present SP-GAN, a new unsupervised sphere-guided generative model for direct synthesis of 3D shapes in the form of point clouds.
Accurate Grid Keypoint Learning for Efficient Video Prediction
Video prediction methods generally consume substantial computing resources in training and deployment, among which keypoint-based approaches show promising improvement in efficiency by simplifying dense image prediction to light keypoint prediction.
Ranked #1 on
Video Prediction
on KTH
FloorLevel-Net: Recognizing Floor-Level Lines with Height-Attention-Guided Multi-task Learning
The ability to recognize the position and order of the floor-level lines that divide adjacent building floors can benefit many applications, for example, urban augmented reality (AR).
Single-Stage Instance Shadow Detection with Bidirectional Relation Learning
Instance shadow detection aims to find shadow instances paired with the objects that cast the shadows.
Ranked #1 on
Instance Shadow Detection
on SOBA
Point Cloud Upsampling via Disentangled Refinement
Point clouds produced by 3D scanning are often sparse, non-uniform, and noisy.
SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud
Lastly, to better exploit hard targets, we design an ODIoU loss to supervise the student with constraints on the predicted box centers and orientations.
Ranked #1 on
Birds Eye View Object Detection
on KITTI Cars Easy
3D-to-2D Distillation for Indoor Scene Parsing
First, we distill 3D knowledge from a pretrained 3D network to supervise a 2D network to learn simulated 3D features from 2D features during the training, so the 2D network can infer without requiring 3D data.
One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation
Point cloud semantic segmentation often requires largescale annotated training data, but clearly, point-wise labels are too tedious to prepare.
Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset With Mechatronic Alignment
Low-light video enhancement is an important task.
On Learning the Right Attention Point for Feature Enhancement
We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e. g., classification and segmentation.
CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud
Existing single-stage detectors for locating objects in point clouds often treat object localization and category classification as separate tasks, so the localization accuracy and classification confidence may not well align.
Ranked #3 on
Birds Eye View Object Detection
on KITTI Cars Easy
DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets
Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains to make the semantic features more discriminative.
Mononizing Binocular Videos
This paper presents the idea ofmono-nizingbinocular videos and a frame-work to effectively realize it.
Image and Video Processing Graphics
Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
To this end, we present a new domain generalization framework that learns how to generalize across domains simultaneously from extrinsic relationship supervision and intrinsic self-supervision for images from multi-source domains.
TilinGNN: Learning to Tile with Self-Supervised Graph Neural Network
To start, we reformulate tiling as a graph problem by modeling candidate tile locations in the target shape as graph nodes and connectivity between tile locations as edges.
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Instance segmentation is an important task for scene understanding.
Ranked #5 on
3D Instance Segmentation
on STPLS3D
A Rotation-Invariant Framework for Deep Point Cloud Analysis
Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to arbitrary orientations.
Non-Local Part-Aware Point Cloud Denoising
This paper presents a novel non-local part-aware deep neural network to denoise point clouds by exploring the inherent non-local self-similarity in 3D objects and scenes.
PointAugment: an Auto-Augmentation Framework for Point Cloud Classification
We present PointAugment, a new auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network.
Ranked #2 on
3D Point Cloud Data Augmentation
on ModelNet40
Instance Shadow Detection
Then, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results.
Ranked #2 on
Instance Shadow Detection
on SOBA
Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world.
CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading
In this paper, we present a novel cross-disease attention network (CANet) to jointly grade DR and DME by exploring the internal relationship between the diseases with only image-level supervision.
Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
To incorporate point features in the edge branch, we establish a hierarchical graph framework, where the graph is initialized from a coarse layer and gradually enriched along the point decoding process.
Ranked #33 on
Semantic Segmentation
on S3DIS Area5
Deep Floor Plan Recognition Using a Multi-Task Network with Room-Boundary-Guided Attention
Besides walls and rooms, we aim to recognize diverse floor plan elements, such as doors, windows and different types of rooms, in the floor layouts.
LassoNet: Deep Lasso-Selection of 3D Point Clouds
A hierarchical network is trained using a dataset with over 30K lasso-selection records on two different point cloud data.
Human-Computer Interaction Graphics
PU-GAN: a Point Cloud Upsampling Adversarial Network
Point clouds acquired from range scans are often sparse, noisy, and non-uniform.
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
We design a novel uncertainty-aware scheme to enable the student model to gradually learn from the meaningful and reliable targets by exploiting the uncertainty information.
Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis
Mutually leveraging both low-level feature sharing and high-level prediction correlating, our MTRCNet-CL method can encourage the interactions between the two tasks to a large extent, and hence can bring about benefits to each other.
Ranked #3 on
Surgical tool detection
on Cholec80
Revisiting Metric Learning for Few-Shot Image Classification
However, the importance of feature embedding, i. e., exploring the relationship among training samples, is neglected.
Difficulty-aware Meta-learning for Rare Disease Diagnosis
Rare diseases have extremely low-data regimes, unlike common diseases with large amount of available labeled data.
Boundary and Entropy-driven Adversarial Learning for Fundus Image Segmentation
The cross-domain discrepancy (domain shift) hinders the generalization of deep neural networks to work on different domain datasets. In this work, we present an unsupervised domain adaptation framework, called Boundary and Entropy-driven Adversarial Learning (BEAL), to improve the OD and OC segmentation performance, especially on the ambiguous boundary regions.
Unsupervised Detection of Distinctive Regions on 3D Shapes
This paper presents a novel approach to learn and detect distinctive regions on 3D shapes.
Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data
This paper presents a new method for shadow removal using unpaired data, enabling us to avoid tedious annotations and obtain more diverse training samples.
SAC-Net: Spatial Attenuation Context for Salient Object Detection
This paper presents a new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects.
Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation
In this paper, we present a novel semi-supervised method for medical image segmentation, where the network is optimized by the weighted combination of a common supervised loss for labeled inputs only and a regularization loss for both labeled and unlabeled data.
Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation
In this paper, we present a novel patchbased Output Space Adversarial Learning framework (pOSAL) to jointly and robustly segment the OD and OC from different fundus image datasets.
Ranked #2 on
Optic Disc Segmentation
on REFUGE
The Liver Tumor Segmentation Benchmark (LiTS)
In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018.
Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection
Second, we develop a bidirectional feature pyramid network (BFPN) to aggregate shadow contexts spanned across different CNN layers by deploying two series of RAR modules in the network to iteratively combine and refine context features: one series to refine context features from deep to shallow layers, and another series from shallow to deep layers.
Ranked #3 on
Shadow Detection
on SBU
Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model
In this paper, we present a novel semi-supervised method for skin lesion segmentation, where the network is optimized by the weighted combination of a common supervised loss for labeled inputs only and a regularization loss for both labeled and unlabeled data.
EC-Net: an Edge-aware Point set Consolidation Network
In this paper, we present the first deep learning based edge-aware technique to facilitate the consolidation of point clouds.
Deeply Supervised Rotation Equivariant Network for Lesion Segmentation in Dermoscopy Images
Our best model achieves 77. 23\%(JA) on the test dataset, outperforming the state-of-the-art challenging methods and further demonstrating the effectiveness of our proposed deeply supervised rotation equivariant segmentation network.
Direction-aware Spatial Context Features for Shadow Detection and Removal
This paper presents a novel deep neural network design for shadow detection and removal by analyzing the spatial image context in a direction-aware manner.
Ranked #6 on
Shadow Removal
on ISTD
PU-Net: Point Cloud Upsampling Network
Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data.
Ranked #3 on
Point Cloud Super Resolution
on SHREC15
Direction-aware Spatial Context Features for Shadow Detection
To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN.
Ranked #2 on
RGB Salient Object Detection
on SBU
Joint Bi-Layer Optimization for Single-Image Rain Streak Removal
A third prior is defined on the rain-streak layer R, based on similarity of patches to the extracted rain patches.
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
Our method outperformed other state-of-the-arts on the segmentation results of tumors and achieved very competitive performance for liver segmentation even with a single model.
Ranked #1 on
Liver Segmentation
on LiTS2017
(Dice metric)
Automatic Liver And Tumor Segmentation
Image Segmentation
+3
A Non-Local Low-Rank Framework for Ultrasound Speckle Reduction
`Speckle' refers to the granular patterns that occur in ultrasound images due to wave interference.
