Jiaming Liu

Jiaming Liu, Qizhe Zhang, Xiaoqi Li et al.

Neuromorphic spike data, an upcoming modality with high temporal resolution, has shown promising potential in autonomous driving by mitigating the challenges posed by high-velocity motion blur. However, training the spike depth estimation network holds significant challenges in two aspects: sparse spatial information for pixel-wise tasks and difficulties in achieving paired depth labels for temporally intensive spike streams. Therefore, we introduce open-source RGB data to support spike depth estimation, leveraging its annotations and spatial information. The inherent differences in modalities and data distribution make it challenging to directly apply transfer learning from open-source RGB to target spike data. To this end, we propose a cross-modality cross-domain (BiCross) framework to realize unsupervised spike depth estimation by introducing simulated mediate source spike data. Specifically, we design a Coarse-to-Fine Knowledge Distillation (CFKD) approach to facilitate comprehensive cross-modality knowledge transfer while preserving the unique strengths of both modalities, utilizing a spike-oriented uncertainty scheme. Then, we propose a Self-Correcting Teacher-Student (SCTS) mechanism to screen out reliable pixel-wise pseudo labels and ease the domain shift of the student model, which avoids error accumulation in target spike data. To verify the effectiveness of BiCross, we conduct extensive experiments on four scenarios, including Synthetic to Real, Extreme Weather, Scene Changing, and Real Spike. Our method achieves state-of-the-art (SOTA) performances, compared with RGB-oriented unsupervised depth estimation methods. Code and dataset: https://github.com/Theia-4869/BiCross

Xiaobao Wei, Renrui Zhang, Jiarui Wu et al.

Neural 3D reconstruction from multi-view images has recently attracted increasing attention from the community. Existing methods normally learn a neural field for the whole scene, while it is still under-explored how to reconstruct a target object indicated by users. Considering the Segment Anything Model (SAM) has shown effectiveness in segmenting any 2D images, in this paper, we propose NTO3D, a novel high-quality Neural Target Object 3D (NTO3D) reconstruction method, which leverages the benefits of both neural field and SAM. We first propose a novel strategy to lift the multi-view 2D segmentation masks of SAM into a unified 3D occupancy field. The 3D occupancy field is then projected into 2D space and generates the new prompts for SAM. This process is iterative until convergence to separate the target object from the scene. After this, we then lift the 2D features of the SAM encoder into a 3D feature field in order to improve the reconstruction quality of the target object. NTO3D lifts the 2D masks and features of SAM into the 3D neural field for high-quality neural target object 3D reconstruction. We conduct detailed experiments on several benchmark datasets to demonstrate the advantages of our method. The code will be available at: https://github.com/ucwxb/NTO3D.

Jinze Yu, Jiaming Liu, Xiaobao Wei et al.

Recently, DEtection TRansformer (DETR), an end-to-end object detection pipeline, has achieved promising performance. However, it requires large-scale labeled data and suffers from domain shift, especially when no labeled data is available in the target domain. To solve this problem, we propose an end-to-end cross-domain detection Transformer based on the mean teacher framework, MTTrans, which can fully exploit unlabeled target domain data in object detection training and transfer knowledge between domains via pseudo labels. We further propose the comprehensive multi-level feature alignment to improve the pseudo labels generated by the mean teacher framework taking advantage of the cross-scale self-attention mechanism in Deformable DETR. Image and object features are aligned at the local, global, and instance levels with domain query-based feature alignment (DQFA), bi-level graph-based prototype alignment (BGPA), and token-wise image feature alignment (TIFA). On the other hand, the unlabeled target domain data pseudo-labeled and available for the object detection training by the mean teacher framework can lead to better feature extraction and alignment. Thus, the mean teacher framework and the comprehensive multi-level feature alignment can be optimized iteratively and mutually based on the architecture of Transformers. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance in three domain adaptation scenarios, especially the result of Sim10k to Cityscapes scenario is remarkably improved from 52.6 mAP to 57.9 mAP. Code will be released.

Yulu Gan, Mingjie Pan, Rongyu Zhang et al. · pku

When facing changing environments in the real world, the lightweight model on client devices suffers from severe performance drops under distribution shifts. The main limitations of the existing device model lie in (1) unable to update due to the computation limit of the device, (2) the limited generalization ability of the lightweight model. Meanwhile, recent large models have shown strong generalization capability on the cloud while they can not be deployed on client devices due to poor computation constraints. To enable the device model to deal with changing environments, we propose a new learning paradigm of Cloud-Device Collaborative Continual Adaptation, which encourages collaboration between cloud and device and improves the generalization of the device model. Based on this paradigm, we further propose an Uncertainty-based Visual Prompt Adapted (U-VPA) teacher-student model to transfer the generalization capability of the large model on the cloud to the device model. Specifically, we first design the Uncertainty Guided Sampling (UGS) to screen out challenging data continuously and transmit the most out-of-distribution samples from the device to the cloud. Then we propose a Visual Prompt Learning Strategy with Uncertainty guided updating (VPLU) to specifically deal with the selected samples with more distribution shifts. We transmit the visual prompts to the device and concatenate them with the incoming data to pull the device testing distribution closer to the cloud training distribution. We conduct extensive experiments on two object detection datasets with continually changing environments. Our proposed U-VPA teacher-student framework outperforms previous state-of-the-art test time adaptation and device-cloud collaboration methods. The code and datasets will be released.

Shangkun Sun, Jiaming Liu, Thomas H. Li et al.

Occlusions between consecutive frames have long posed a significant challenge in optical flow estimation. The inherent ambiguity introduced by occlusions directly violates the brightness constancy constraint and considerably hinders pixel-to-pixel matching. To address this issue, multi-frame optical flow methods leverage adjacent frames to mitigate the local ambiguity. Nevertheless, prior multi-frame methods predominantly adopt recursive flow estimation, resulting in a considerable computational overlap. In contrast, we propose a streamlined in-batch framework that eliminates the need for extensive redundant recursive computations while concurrently developing effective spatio-temporal modeling approaches under in-batch estimation constraints. Specifically, we present a Streamlined In-batch Multi-frame (SIM) pipeline tailored to video input, attaining a similar level of time efficiency to two-frame networks. Furthermore, we introduce an efficient Integrative Spatio-temporal Coherence (ISC) modeling method for effective spatio-temporal modeling during the encoding phase, which introduces no additional parameter overhead. Additionally, we devise a Global Temporal Regressor (GTR) that effectively explores temporal relations during decoding. Benefiting from the efficient SIM pipeline and effective modules, StreamFlow not only excels in terms of performance on the challenging KITTI and Sintel datasets, with particular improvement in occluded areas but also attains a remarkable $63.82\%$ enhancement in speed compared with previous multi-frame methods. The code will be available soon at https://github.com/littlespray/StreamFlow.

Yingping Liang, Jiaming Liu, Debing Zhang et al.

The accuracy of learning-based optical flow estimation models heavily relies on the realism of the training datasets. Current approaches for generating such datasets either employ synthetic data or generate images with limited realism. However, the domain gap of these data with real-world scenes constrains the generalization of the trained model to real-world applications. To address this issue, we investigate generating realistic optical flow datasets from real-world images. Firstly, to generate highly realistic new images, we construct a layered depth representation, known as multiplane images (MPI), from single-view images. This allows us to generate novel view images that are highly realistic. To generate optical flow maps that correspond accurately to the new image, we calculate the optical flows of each plane using the camera matrix and plane depths. We then project these layered optical flows into the output optical flow map with volume rendering. Secondly, to ensure the realism of motion, we present an independent object motion module that can separate the camera and dynamic object motion in MPI. This module addresses the deficiency in MPI-based single-view methods, where optical flow is generated only by camera motion and does not account for any object movement. We additionally devise a depth-aware inpainting module to merge new images with dynamic objects and address unnatural motion occlusions. We show the superior performance of our method through extensive experiments on real-world datasets. Moreover, our approach achieves state-of-the-art performance in both unsupervised and supervised training of learning-based models. The code will be made publicly available at: \url{https://github.com/Sharpiless/MPI-Flow}.

Xiaowei Chi, Jiaming Liu, Ming Lu et al.

Bird's-Eye-View (BEV) 3D Object Detection is a crucial multi-view technique for autonomous driving systems. Recently, plenty of works are proposed, following a similar paradigm consisting of three essential components, i.e., camera feature extraction, BEV feature construction, and task heads. Among the three components, BEV feature construction is BEV-specific compared with 2D tasks. Existing methods aggregate the multi-view camera features to the flattened grid in order to construct the BEV feature. However, flattening the BEV space along the height dimension fails to emphasize the informative features of different heights. For example, the barrier is located at a low height while the truck is located at a high height. In this paper, we propose a novel method named BEV Slice Attention Network (BEV-SAN) for exploiting the intrinsic characteristics of different heights. Instead of flattening the BEV space, we first sample along the height dimension to build the global and local BEV slices. Then, the features of BEV slices are aggregated from the camera features and merged by the attention mechanism. Finally, we fuse the merged local and global BEV features by a transformer to generate the final feature map for task heads. The purpose of local BEV slices is to emphasize informative heights. In order to find them, we further propose a LiDAR-guided sampling strategy to leverage the statistical distribution of LiDAR to determine the heights of local slices. Compared with uniform sampling, LiDAR-guided sampling can determine more informative heights. We conduct detailed experiments to demonstrate the effectiveness of BEV-SAN. Code will be released.

Xiaoqi Li, Yanzi Wang, Yan Shen et al.

In the realm of future home-assistant robots, 3D articulated object manipulation is essential for enabling robots to interact with their environment. Many existing studies make use of 3D point clouds as the primary input for manipulation policies. However, this approach encounters challenges due to data sparsity and the significant cost associated with acquiring point cloud data, which can limit its practicality. In contrast, RGB images offer high-resolution observations using cost effective devices but lack spatial 3D geometric information. To overcome these limitations, we present a novel image-based robotic manipulation framework. This framework is designed to capture multiple perspectives of the target object and infer depth information to complement its geometry. Initially, the system employs an eye-on-hand RGB camera to capture an overall view of the target object. It predicts the initial depth map and a coarse affordance map. The affordance map indicates actionable areas on the object and serves as a constraint for selecting subsequent viewpoints. Based on the global visual prior, we adaptively identify the optimal next viewpoint for a detailed observation of the potential manipulation success area. We leverage geometric consistency to fuse the views, resulting in a refined depth map and a more precise affordance map for robot manipulation decisions. By comparing with prior works that adopt point clouds or RGB images as inputs, we demonstrate the effectiveness and practicality of our method. In the project webpage (https://sites.google.com/view/imagemanip), real world experiments further highlight the potential of our method for practical deployment.

Jiaming Liu, Yue Wu, Maoguo Gong et al.

3D Single Object Tracking (SOT) stands a forefront task of computer vision, proving essential for applications like autonomous driving. Sparse and occluded data in scene point clouds introduce variations in the appearance of tracked objects, adding complexity to the task. In this research, we unveil M3SOT, a novel 3D SOT framework, which synergizes multiple input frames (template sets), multiple receptive fields (continuous contexts), and multiple solution spaces (distinct tasks) in ONE model. Remarkably, M3SOT pioneers in modeling temporality, contexts, and tasks directly from point clouds, revisiting a perspective on the key factors influencing SOT. To this end, we design a transformer-based network centered on point cloud targets in the search area, aggregating diverse contextual representations and propagating target cues by employing historical frames. As M3SOT spans varied processing perspectives, we've streamlined the network-trimming its depth and optimizing its structure-to ensure a lightweight and efficient deployment for SOT applications. We posit that, backed by practical construction, M3SOT sidesteps the need for complex frameworks and auxiliary components to deliver sterling results. Extensive experiments on benchmarks such as KITTI, nuScenes, and Waymo Open Dataset demonstrate that M3SOT achieves state-of-the-art performance at 38 FPS. Our code and models are available at https://github.com/ywu0912/TeamCode.git.

Jiaming Liu, Ming Lu, Kaixin Chen et al.

Internet video delivery has undergone a tremendous explosion of growth over the past few years. However, the quality of video delivery system greatly depends on the Internet bandwidth. Deep Neural Networks (DNNs) are utilized to improve the quality of video delivery recently. These methods divide a video into chunks, and stream LR video chunks and corresponding content-aware models to the client. The client runs the inference of models to super-resolve the LR chunks. Consequently, a large number of models are streamed in order to deliver a video. In this paper, we first carefully study the relation between models of different chunks, then we tactfully design a joint training framework along with the Content-aware Feature Modulation (CaFM) layer to compress these models for neural video delivery. {\bf With our method, each video chunk only requires less than $1\% $ of original parameters to be streamed, achieving even better SR performance.} We conduct extensive experiments across various SR backbones, video time length, and scaling factors to demonstrate the advantages of our method. Besides, our method can be also viewed as a new approach of video coding. Our primary experiments achieve better video quality compared with the commercial H.264 and H.265 standard under the same storage cost, showing the great potential of the proposed method. Code is available at:\url{https://github.com/Neural-video-delivery/CaFM-Pytorch-ICCV2021}

He guo, Xiameng Qin, Jiaming Liu et al.

Extracting entity from images is a crucial part of many OCR applications, such as entity recognition of cards, invoices, and receipts. Most of the existing works employ classical detection and recognition paradigm. This paper proposes an Entity-aware Attention Text Extraction Network called EATEN, which is an end-to-end trainable system to extract the entities without any post-processing. In the proposed framework, each entity is parsed by its corresponding entity-aware decoder, respectively. Moreover, we innovatively introduce a state transition mechanism which further improves the robustness of entity extraction. In consideration of the absence of public benchmarks, we construct a dataset of almost 0.6 million images in three real-world scenarios (train ticket, passport and business card), which is publicly available at https://github.com/beacandler/EATEN. To the best of our knowledge, EATEN is the first single shot method to extract entities from images. Extensive experiments on these benchmarks demonstrate the state-of-the-art performance of EATEN.

Senqiao Yang, Jiaming Liu, Ray Zhang et al.

Recently, Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have shown promise in instruction following and 2D image understanding. While these models are powerful, they have not yet been developed to comprehend the more challenging 3D physical scenes, especially when it comes to the sparse outdoor LiDAR data. In this paper, we introduce LiDAR-LLM, which takes raw LiDAR data as input and harnesses the remarkable reasoning capabilities of LLMs to gain a comprehensive understanding of outdoor 3D scenes. The central insight of our LiDAR-LLM is the reformulation of 3D outdoor scene cognition as a language modeling problem, encompassing tasks such as 3D captioning, 3D grounding, 3D question answering, etc. Specifically, due to the scarcity of 3D LiDAR-text pairing data, we introduce a three-stage training strategy and generate relevant datasets, progressively aligning the 3D modality with the language embedding space of LLM. Furthermore, we design a View-Aware Transformer (VAT) to connect the 3D encoder with the LLM, which effectively bridges the modality gap and enhances the LLM's spatial orientation comprehension of visual features. Our experiments show that LiDAR-LLM possesses favorable capabilities to comprehend various instructions regarding 3D scenes and engage in complex spatial reasoning. LiDAR-LLM attains a 40.9 BLEU-1 on the 3D captioning task and achieves a 63.1\% classification accuracy and a 14.3\% BEV mIoU on the 3D grounding task. Web page: https://sites.google.com/view/lidar-llm

Yueru Jia, Jiaming Liu, Sixiang Chen et al.

3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has increasingly focused on the explicit extraction of 3D features, while still facing challenges such as the lack of large-scale robotic 3D data and the potential loss of spatial geometry. To address these limitations, we propose the Lift3D framework, which progressively enhances 2D foundation models with implicit and explicit 3D robotic representations to construct a robust 3D manipulation policy. Specifically, we first design a task-aware masked autoencoder that masks task-relevant affordance patches and reconstructs depth information, enhancing the 2D foundation model's implicit 3D robotic representation. After self-supervised fine-tuning, we introduce a 2D model-lifting strategy that establishes a positional mapping between the input 3D points and the positional embeddings of the 2D model. Based on the mapping, Lift3D utilizes the 2D foundation model to directly encode point cloud data, leveraging large-scale pretrained knowledge to construct explicit 3D robotic representations while minimizing spatial information loss. In experiments, Lift3D consistently outperforms previous state-of-the-art methods across several simulation benchmarks and real-world scenarios.

Xiangyang Zhu, Renrui Zhang, Bowei He et al.

To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot segmentation methods first pre-train models on 'seen' classes, and then evaluate their generalization performance on 'unseen' classes. However, the prior pre-training stage not only introduces excessive time overhead but also incurs a significant domain gap on 'unseen' classes. To tackle these issues, we propose a Non-parametric Network for few-shot 3D Segmentation, Seg-NN, and its Parametric variant, Seg-PN. Without training, Seg-NN extracts dense representations by hand-crafted filters and achieves comparable performance to existing parametric models. Due to the elimination of pre-training, Seg-NN can alleviate the domain gap issue and save a substantial amount of time. Based on Seg-NN, Seg-PN only requires training a lightweight QUEry-Support Transferring (QUEST) module, which enhances the interaction between the support set and query set. Experiments suggest that Seg-PN outperforms previous state-of-the-art method by +4.19% and +7.71% mIoU on S3DIS and ScanNet datasets respectively, while reducing training time by -90%, indicating its effectiveness and efficiency.

Guanqun Wang, Jiaming Liu, Chenxuan Li et al.

The burgeoning field of Multimodal Large Language Models (MLLMs) has exhibited remarkable performance in diverse tasks such as captioning, commonsense reasoning, and visual scene understanding. However, the deployment of these large-scale MLLMs on client devices is hindered by their extensive model parameters, leading to a notable decline in generalization capabilities when these models are compressed for device deployment. Addressing this challenge, we introduce a Cloud-Device Collaborative Continual Adaptation framework, designed to enhance the performance of compressed, device-deployed MLLMs by leveraging the robust capabilities of cloud-based, larger-scale MLLMs. Our framework is structured into three key components: a device-to-cloud uplink for efficient data transmission, cloud-based knowledge adaptation, and an optimized cloud-to-device downlink for model deployment. In the uplink phase, we employ an Uncertainty-guided Token Sampling (UTS) strategy to effectively filter out-of-distribution tokens, thereby reducing transmission costs and improving training efficiency. On the cloud side, we propose Adapter-based Knowledge Distillation (AKD) method to transfer refined knowledge from large-scale to compressed, pocket-size MLLMs. Furthermore, we propose a Dynamic Weight update Compression (DWC) strategy for the downlink, which adaptively selects and quantizes updated weight parameters, enhancing transmission efficiency and reducing the representational disparity between cloud and device models. Extensive experiments on several multimodal benchmarks demonstrate the superiority of our proposed framework over prior Knowledge Distillation and device-cloud collaboration methods. Notably, we also validate the feasibility of our approach to real-world experiments.

Yingping Liang, Ying Fu, Yutao Hu et al.

Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied to real-world applications and limits the benefits of scaling up datasets. To address these challenges, we propose \textbf{Flow-Anything}, a large-scale data generation framework designed to learn optical flow estimation from any single-view images in the real world. We employ two effective steps to make data scaling-up promising. First, we convert a single-view image into a 3D representation using advanced monocular depth estimation networks. This allows us to render optical flow and novel view images under a virtual camera. Second, we develop an Object-Independent Volume Rendering module and a Depth-Aware Inpainting module to model the dynamic objects in the 3D representation. These two steps allow us to generate realistic datasets for training from large-scale single-view images, namely \textbf{FA-Flow Dataset}. For the first time, we demonstrate the benefits of generating optical flow training data from large-scale real-world images, outperforming the most advanced unsupervised methods and supervised methods on synthetic datasets. Moreover, our models serve as a foundation model and enhance the performance of various downstream video tasks.

Hongzhi Gao, Zheng Chen, Zehui Chen et al.

Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming. Therefore, the form of point annotations is proposed to offer significant prospects for practical applications in 3D detection, which is not only more accessible and less expensive but also provides strong spatial information for object localization. In this paper, we empirically discover that it is non-trivial to merely adapt Point-DETR to its 3D form, encountering two main bottlenecks: 1) it fails to encode strong 3D prior into the model, and 2) it generates low-quality pseudo labels in distant regions due to the extreme sparsity of LiDAR points. To overcome these challenges, we introduce Point-DETR3D, a teacher-student framework for weakly semi-supervised 3D detection, designed to fully capitalize on point-wise supervision within a constrained instance-wise annotation budget.Different from Point-DETR which encodes 3D positional information solely through a point encoder, we propose an explicit positional query initialization strategy to enhance the positional prior. Considering the low quality of pseudo labels at distant regions produced by the teacher model, we enhance the detector's perception by incorporating dense imagery data through a novel Cross-Modal Deformable RoI Fusion (D-RoI).Moreover, an innovative point-guided self-supervised learning technique is proposed to allow for fully exploiting point priors, even in student models.Extensive experiments on representative nuScenes dataset demonstrate our Point-DETR3D obtains significant improvements compared to previous works. Notably, with only 5% of labeled data, Point-DETR3D achieves over 90% performance of its fully supervised counterpart.

Yipeng Sun, Jiaming Liu, Wei Liu et al.

Most existing text reading benchmarks make it difficult to evaluate the performance of more advanced deep learning models in large vocabularies due to the limited amount of training data. To address this issue, we introduce a new large-scale text reading benchmark dataset named Chinese Street View Text (C-SVT) with 430,000 street view images, which is at least 14 times as large as the existing Chinese text reading benchmarks. To recognize Chinese text in the wild while keeping large-scale datasets labeling cost-effective, we propose to annotate one part of the CSVT dataset (30,000 images) in locations and text labels as full annotations and add 400,000 more images, where only the corresponding text-of-interest in the regions is given as weak annotations. To exploit the rich information from the weakly annotated data, we design a text reading network in a partially supervised learning framework, which enables to localize and recognize text, learn from fully and weakly annotated data simultaneously. To localize the best matched text proposals from weakly labeled images, we propose an online proposal matching module incorporated in the whole model, spotting the keyword regions by sharing parameters for end-to-end training. Compared with fully supervised training algorithms, this model can improve the end-to-end recognition performance remarkably by 4.03% in F-score at the same labeling cost. The proposed model can also achieve state-of-the-art results on the ICDAR 2017-RCTW dataset, which demonstrates the effectiveness of the proposed partially supervised learning framework.

Yi He, Jiayuan Shi, Chuan Wang et al.

In this paper we present a new data-driven method for robust skin detection from a single human portrait image. Unlike previous methods, we incorporate human body as a weak semantic guidance into this task, considering acquiring large-scale of human labeled skin data is commonly expensive and time-consuming. To be specific, we propose a dual-task neural network for joint detection of skin and body via a semi-supervised learning strategy. The dual-task network contains a shared encoder but two decoders for skin and body separately. For each decoder, its output also serves as a guidance for its counterpart, making both decoders mutually guided. Extensive experiments were conducted to demonstrate the effectiveness of our network with mutual guidance, and experimental results show our network outperforms the state-of-the-art in skin detection.

Yifan Ding, Chuan Wang, Haibin Huang et al.

In this paper, we present a new inpainting framework for recovering missing regions of video frames. Compared with image inpainting, performing this task on video presents new challenges such as how to preserving temporal consistency and spatial details, as well as how to handle arbitrary input video size and length fast and efficiently. Towards this end, we propose a novel deep learning architecture which incorporates ConvLSTM and optical flow for modeling the spatial-temporal consistency in videos. It also saves much computational resource such that our method can handle videos with larger frame size and arbitrary length streamingly in real-time. Furthermore, to generate an accurate optical flow from corrupted frames, we propose a robust flow generation module, where two sources of flows are fed and a flow blending network is trained to fuse them. We conduct extensive experiments to evaluate our method in various scenarios and different datasets, both qualitatively and quantitatively. The experimental results demonstrate the superior of our method compared with the state-of-the-art inpainting approaches.

Yipeng Sun, Chengquan Zhang, Zuming Huang et al.

Reading text from images remains challenging due to multi-orientation, perspective distortion and especially the curved nature of irregular text. Most of existing approaches attempt to solve the problem in two or multiple stages, which is considered to be the bottleneck to optimize the overall performance. To address this issue, we propose an end-to-end trainable network architecture, named TextNet, which is able to simultaneously localize and recognize irregular text from images. Specifically, we develop a scale-aware attention mechanism to learn multi-scale image features as a backbone network, sharing fully convolutional features and computation for localization and recognition. In text detection branch, we directly generate text proposals in quadrangles, covering oriented, perspective and curved text regions. To preserve text features for recognition, we introduce a perspective RoI transform layer, which can align quadrangle proposals into small feature maps. Furthermore, in order to extract effective features for recognition, we propose to encode the aligned RoI features by RNN into context information, combining spatial attention mechanism to generate text sequences. This overall pipeline is capable of handling both regular and irregular cases. Finally, text localization and recognition tasks can be jointly trained in an end-to-end fashion with designed multi-task loss. Experiments on standard benchmarks show that the proposed TextNet can achieve state-of-the-art performance, and outperform existing approaches on irregular datasets by a large margin.