arXiv subjects

Wei Hua

Publications and source records attributed to Wei Hua.

At least 37 records · Page 2Linked to original sources

arXiv2023

ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images

Structured text extraction is one of the most valuable and challenging application directions in the field of Document AI. However, the scenarios of past benchmarks are limited, and the corresponding evaluation protocols usually focus on the submodules of the structured text extraction scheme. In order to eliminate these problems, we organized the ICDAR 2023 competition on Structured text extraction from Visually-Rich Document images (SVRD). We set up two tracks for SVRD including Track 1: HUST-CELL and Track 2: Baidu-FEST, where HUST-CELL aims to evaluate the end-to-end performance of Complex Entity Linking and Labeling, and Baidu-FEST focuses on evaluating the performance and generalization of Zero-shot / Few-shot Structured Text extraction from an end-to-end perspective. Compared to the current document benchmarks, our two tracks of competition benchmark enriches the scenarios greatly and contains more than 50 types of visually-rich document images (mainly from the actual enterprise applications). The competition opened on 30th December, 2022 and closed on 24th March, 2023. There are 35 participants and 91 valid submissions received for Track 1, and 15 participants and 26 valid submissions received for Track 2. In this report we will presents the motivation, competition datasets, task definition, evaluation protocol, and submission summaries. According to the performance of the submissions, we believe there is still a large gap on the expected information extraction performance for complex and zero-shot scenarios. It is hoped that this competition will attract many researchers in the field of CV and NLP, and bring some new thoughts to the field of Document AI.

cs.CV↗

arXiv2023

SOOD: Towards Semi-Supervised Oriented Object Detection

Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches mainly focus on horizontal objects, leaving multi-oriented objects that are common in aerial images unexplored. This paper proposes a novel Semi-supervised Oriented Object Detection model, termed SOOD, built upon the mainstream pseudo-labeling framework. Towards oriented objects in aerial scenes, we design two loss functions to provide better supervision. Focusing on the orientations of objects, the first loss regularizes the consistency between each pseudo-label-prediction pair (includes a prediction and its corresponding pseudo label) with adaptive weights based on their orientation gap. Focusing on the layout of an image, the second loss regularizes the similarity and explicitly builds the many-to-many relation between the sets of pseudo-labels and predictions. Such a global consistency constraint can further boost semi-supervised learning. Our experiments show that when trained with the two proposed losses, SOOD surpasses the state-of-the-art SSOD methods under various settings on the DOTA-v1.5 benchmark. The code will be available at https://github.com/HamPerdredes/SOOD.

cs.CV↗

arXiv2023

I$^2$-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs

In this work, we present I$^2$-SDF, a new method for intrinsic indoor scene reconstruction and editing using differentiable Monte Carlo raytracing on neural signed distance fields (SDFs). Our holistic neural SDF-based framework jointly recovers the underlying shapes, incident radiance and materials from multi-view images. We introduce a novel bubble loss for fine-grained small objects and error-guided adaptive sampling scheme to largely improve the reconstruction quality on large-scale indoor scenes. Further, we propose to decompose the neural radiance field into spatially-varying material of the scene as a neural field through surface-based, differentiable Monte Carlo raytracing and emitter semantic segmentations, which enables physically based and photorealistic scene relighting and editing applications. Through a number of qualitative and quantitative experiments, we demonstrate the superior quality of our method on indoor scene reconstruction, novel view synthesis, and scene editing compared to state-of-the-art baselines.

cs.CV↗

arXiv2023

Turning a CLIP Model into a Scene Text Detector

The recent large-scale Contrastive Language-Image Pretraining (CLIP) model has shown great potential in various downstream tasks via leveraging the pretrained vision and language knowledge. Scene text, which contains rich textual and visual information, has an inherent connection with a model like CLIP. Recently, pretraining approaches based on vision language models have made effective progresses in the field of text detection. In contrast to these works, this paper proposes a new method, termed TCM, focusing on Turning the CLIP Model directly for text detection without pretraining process. We demonstrate the advantages of the proposed TCM as follows: (1) The underlying principle of our framework can be applied to improve existing scene text detector. (2) It facilitates the few-shot training capability of existing methods, e.g., by using 10% of labeled data, we significantly improve the performance of the baseline method with an average of 22% in terms of the F-measure on 4 benchmarks. (3) By turning the CLIP model into existing scene text detection methods, we further achieve promising domain adaptation ability. The code will be publicly released at https://github.com/wenwenyu/TCM.

cs.CV↗

arXiv2023

SASFormer: Transformers for Sparsely Annotated Semantic Segmentation

Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a multi-stage training strategy. In this work, we propose a simple yet effective sparse annotated semantic segmentation framework based on segformer, dubbed SASFormer, that achieves remarkable performance. Specifically, the framework first generates hierarchical patch attention maps, which are then multiplied by the network predictions to produce correlated regions separated by valid labels. Besides, we also introduce the affinity loss to ensure consistency between the features of correlation results and network predictions. Extensive experiments showcase that our proposed approach is superior to existing methods and achieves cutting-edge performance. The source code is available at \url{https://github.com/su-hui-zz/SASFormer}.

cs.CV↗

arXiv2023

PriorLane: A Prior Knowledge Enhanced Lane Detection Approach Based on Transformer

Lane detection is one of the fundamental modules in self-driving. In this paper we employ a transformer-only method for lane detection, thus it could benefit from the blooming development of fully vision transformer and achieve the state-of-the-art (SOTA) performance on both CULane and TuSimple benchmarks, by fine-tuning the weight fully pre-trained on large datasets. More importantly, this paper proposes a novel and general framework called PriorLane, which is used to enhance the segmentation performance of the fully vision transformer by introducing the low-cost local prior knowledge. Specifically, PriorLane utilizes an encoder-only transformer to fuse the feature extracted by a pre-trained segmentation model with prior knowledge embeddings. Note that a Knowledge Embedding Alignment (KEA) module is adapted to enhance the fusion performance by aligning the knowledge embedding. Extensive experiments on our Zjlab dataset show that PriorLane outperforms SOTA lane detection methods by a 2.82% mIoU when prior knowledge is employed, and the code will be released at: https://github.com/vincentqqb/PriorLane.

cs.CV↗

arXiv2022

Dynamic Speed Guidance for CAV Ramp Merging in Non-Cooperative Environment: An On-Site Experiment

Ramp merging is a typical application of cooperative intelligent transportation system (C-ITS). Vehicle trajectories perceived by roadside sensors are importation complement to the limited visual field of on-board perception. Vehicle tracking and trajectory denoising algorithm is proposed in this paper to take full advantage of roadside cameras for vehicle trajectory and speed profile estimation. Dynamic speed guidance algorithm is proposed to help on-ramp vehicles to merge into mainline smoothly, even in non-cooperative environment where mainline vehicles are not expected to slow down to accommodate on-ramp vehicles. On-site experiments were taken out in a merging area of Hangzhou Belt Highway to testify our prototype system, and simulation analysis shows our proposed algorithm can achieve significant fuel savings during the ramp merging process.

cs.RO↗

arXiv2022

CVR-LSE: Compact Vectorization Representation of Local Static Environments for Unmanned Ground Vehicles

According to the requirement of general static obstacle detection, this paper proposes a compact vectorization representation approach of local static environments for unmanned ground vehicles. At first, by fusing the data of LiDAR and IMU, high-frequency pose information is obtained. Then, through the two-dimensional (2D) obstacle points generation, the process of grid map maintenance with a fixed size is proposed. Finally, the local static environment is described via multiple convex polygons, which is realized throungh the double threshold-based boundary simplification and the convex polygon segmentation. Our proposed approach has been applied in a practical driverless project in the park, and the qualitative experimental results on typical scenes verify the effectiveness and robustness. In addition, the quantitative evaluation shows the superior performance on making use of fewer number of points information (decreased by about 60%) to represent the local static environment compared with the traditional grid map-based methods. Furthermore, the performance of running time (15ms) shows that the proposed approach can be used for real-time local static environment perception. The corresponding code can be accessed at https://github.com/ghm0819/cvr_lse.

cs.RO↗

arXiv2022

An Interactive Image-based Modeling System

This paper propose a interactive 3D modeling method and corresponding system based on single or multiple uncalibrated images. The main feature of this method is that, according to the modeling habits of ordinary people, the 3D model of the target is reconstructed from coarse to fine images. On the basis of determining the approximate shape, the user adds or modify projection constraints and spatial constraints, and apply topology modification, gradually realize camera calibration, refine rough model, and finally complete the reconstruction of objects with arbitrary geometry and topology. During the interactive process, the geometric parameters and camera projection matrix are solved in real time, and the reconstruction results are displayed in a 3D window.

cs.CV↗

arXiv2022

Real-time Rendering and Editing of Scattering Effects for Translucent Objects

The photorealistic rendering of the transparent effect of translucent objects is a hot research topic in recent years. A real-time photorealistic rendering and material dynamic editing method for the diffuse scattering effect of translucent objects is proposed based on the bidirectional surface scattering reflectance function's (BSSRDF) Dipole approximation. The diffuse scattering material function in the Dipo le approximation is decomposed into the product form of the shape-related function and the translucent material-related function through principal component analysis; using this decomposition representation, under the real-time photorealistic rendering framework of pre-radiative transmission and the scattering transmission to realize real-time editing of translucent object materials under various light sources. In addition, a method for quadratic wavelet compression of precomputed radiative transfer data in the spatial domain is also proposed. Using the correlation of surface points in the spatial distribution position, on the premise of ensuring the rendering quality, the data is greatly compressed and the rendering is efficiently improved. The experimental results show that the method in this paper can generate a highly realistic translucent effect and ensure the real-time rendering speed.

cs.GR↗

arXiv2022

A Virtual Point Light Generation Method in Close-Range Area

This paper proposes a new hybrid algorithm for sampling virtual point light (VPL). The indirect lighting calculation of the scene is used to distribute the VPL reasonably. In the process of generating VPL, we divide the scene into two parts according to the camera position and orientation. The close-range part: the part that the camera pays attention to. The distant-range part: the part that the camera does not pay attention to or rarely pays attention to. For the close-range part, we use a patch-based vPL sampling method to distribute the VPL as evenly as possible on the patch in the near-field area; for the distant-range part, we use sparse instant radiosity (IR) for sampling. It turns out that, in contrast to conventional multiple instant radiance Compared with the VPL generation algorithm, the method proposed in this paper can greatly improve the quality of the final result graph when the number of VPLs is the same; Under the same rendering quality, the rendering speed can be greatly improved.

cs.GR↗

arXiv2022

Variational Hierarchical Directed Bounding Box Construction for Solid Mesh Models

Object oriented bounding box tree (OBB-Tree for short) has many applications in collision detection, real-time rendering, etc. It has a wide range of applications. The construction of the hierarchical directed bounding box of the solid mesh model is studied, and a new optimization solution method is proposed. But this part of the external space volume that does not belong to the solid mesh model is used as the error, and an error calculation method based on hardware acceleration is given. Secondly, the hierarchical bounding box construction problem is transformed into a variational approximation problem, and the optimal hierarchical directed bounding box is obtained by solving the global error minimum. In the optimization calculation, we propose that combining Lloyd clustering iteration in the same layer and MultiGrid-like reciprocating iteration between layers. Compared with previous results, this method can generate aired original solid mesh models are more tightly packed with hierarchical directed bounding box approximation. In the practical application of collision detection, the results constructed using this method can reduce the computational time of collision detection and improve detection efficiency.

cs.GR↗

arXiv2021

Color Contrast Enhanced Rendering for Optical See-through Head-mounted Displays

Most commercially available optical see-through head-mounted displays (OST-HMDs) utilize optical combiners to simultaneously visualize the physical background and virtual objects. The displayed images perceived by users are a blend of rendered pixels and background colors. Enabling high fidelity color perception in mixed reality (MR) scenarios using OST-HMDs is an important but challenging task. We propose a real-time rendering scheme to enhance the color contrast between virtual objects and the surrounding background for OST-HMDs. Inspired by the discovery of color perception in psychophysics, we first formulate the color contrast enhancement as a constrained optimization problem. We then design an end-to-end algorithm to search the optimal complementary shift in both chromaticity and luminance of the displayed color. This aims at enhancing the contrast between virtual objects and the real background as well as keeping the consistency with the original color. We assess the performance of our approach using a simulated OST-HMD environment and an off-the-shelf OST-HMD. Experimental results from objective evaluations and subjective user studies demonstrate that the proposed approach makes rendered virtual objects more distinguishable from the surrounding background, thereby bringing a better visual experience.

cs.GR↗

arXiv2020

AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification

Convolutional operations have two limitations: (1) do not explicitly model where to focus as the same filter is applied to all the positions, and (2) are unsuitable for modeling long-range dependencies as they only operate on a small neighborhood. While both limitations can be alleviated by attention operations, many design choices remain to be determined to use attention, especially when applying attention to videos. Towards a principled way of applying attention to videos, we address the task of spatiotemporal attention cell search. We propose a novel search space for spatiotemporal attention cells, which allows the search algorithm to flexibly explore various design choices in the cell. The discovered attention cells can be seamlessly inserted into existing backbone networks, e.g., I3D or S3D, and improve video classification accuracy by more than 2% on both Kinetics-600 and MiT datasets. The discovered attention cells outperform non-local blocks on both datasets, and demonstrate strong generalization across different modalities, backbones, and datasets. Inserting our attention cells into I3D-R50 yields state-of-the-art performance on both datasets.

cs.CV↗

arXiv2019

MediaPipe: A Framework for Building Perception Pipelines

Building applications that perceive the world around them is challenging. A developer needs to (a) select and develop corresponding machine learning algorithms and models, (b) build a series of prototypes and demos, (c) balance resource consumption against the quality of the solutions, and finally (d) identify and mitigate problematic cases. The MediaPipe framework addresses all of these challenges. A developer can use MediaPipe to build prototypes by combining existing perception components, to advance them to polished cross-platform applications and measure system performance and resource consumption on target platforms. We show that these features enable a developer to focus on the algorithm or model development and use MediaPipe as an environment for iteratively improving their application with results reproducible across different devices and platforms. MediaPipe will be open-sourced at https://github.com/google/mediapipe.

cs.DC↗

arXiv2019

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale image classification. In this paper, we study NAS for semantic image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space, but becomes increasingly problematic for dense image prediction which exhibits a lot more network level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network level search space that includes many popular designs, and develop a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for semantic image segmentation, attains state-of-the-art performance without any ImageNet pretraining.

cs.CV↗

arXiv2019

Advantages of the multinucleon transfer reactions based on 238U target for producing neutron-rich isotopes around N = 126

The mechanism of multinucleon transfer (MNT) reactions for producing neutron-rich heavy nuclei around N = 126 is investigated within two different theoretical frameworks: dinuclear system (DNS) model and isospin-dependent quantum molecular dynamics (IQMD) model. The effects of mass asymmetry relaxation, N=Z equilibration, and shell closures on production cross sections of neutron-rich heavy nuclei are investigated. For the first time, the advantages for producing neutron-rich heavy nuclei around N = 126 is found in MNT reactions based on 238U target. We propose the reactions with 238U target for producing unknown neutron-rich heavy nuclei around N = 126 in the future.

nucl-th↗

arXiv2018

Progressive Neural Architecture Search

We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms. Our approach uses a sequential model-based optimization (SMBO) strategy, in which we search for structures in order of increasing complexity, while simultaneously learning a surrogate model to guide the search through structure space. Direct comparison under the same search space shows that our method is up to 5 times more efficient than the RL method of Zoph et al. (2018) in terms of number of models evaluated, and 8 times faster in terms of total compute. The structures we discover in this way achieve state of the art classification accuracies on CIFAR-10 and ImageNet.

cs.CV↗