Yi Li

Wenbo Hu, Yifan Xu, Yi Li et al. · harvard

Vision Language Models (VLMs), which extend Large Language Models (LLM) by incorporating visual understanding capability, have demonstrated significant advancements in addressing open-ended visual question-answering (VQA) tasks. However, these models cannot accurately interpret images infused with text, a common occurrence in real-world scenarios. Standard procedures for extracting information from images often involve learning a fixed set of query embeddings. These embeddings are designed to encapsulate image contexts and are later used as soft prompt inputs in LLMs. Yet, this process is limited to the token count, potentially curtailing the recognition of scenes with text-rich context. To improve upon them, the present study introduces BLIVA: an augmented version of InstructBLIP with Visual Assistant. BLIVA incorporates the query embeddings from InstructBLIP and also directly projects encoded patch embeddings into the LLM, a technique inspired by LLaVA. This approach assists the model to capture intricate details potentially missed during the query decoding process. Empirical evidence demonstrates that our model, BLIVA, significantly enhances performance in processing text-rich VQA benchmarks (up to 17.76% in OCR-VQA benchmark) and in undertaking general (not particularly text-rich) VQA benchmarks (up to 7.9% in Visual Spatial Reasoning benchmark), and achieved 17.72% overall improvement in a comprehensive multimodal LLM benchmark (MME), comparing to our baseline InstructBLIP. BLIVA demonstrates significant capability in decoding real-world images, irrespective of text presence. To demonstrate the broad industry applications enabled by BLIVA, we evaluate the model using a new dataset comprising YouTube thumbnails paired with question-answer sets across 11 diverse categories. Our code and models are freely accessible at https://github.com/mlpc-ucsd/BLIVA.

Zekun Qi, Runpei Dong, Guofan Fan et al.

Mainstream 3D representation learning approaches are built upon contrastive or generative modeling pretext tasks, where great improvements in performance on various downstream tasks have been achieved. However, we find these two paradigms have different characteristics: (i) contrastive models are data-hungry that suffer from a representation over-fitting issue; (ii) generative models have a data filling issue that shows inferior data scaling capacity compared to contrastive models. This motivates us to learn 3D representations by sharing the merits of both paradigms, which is non-trivial due to the pattern difference between the two paradigms. In this paper, we propose Contrast with Reconstruct (ReCon) that unifies these two paradigms. ReCon is trained to learn from both generative modeling teachers and single/cross-modal contrastive teachers through ensemble distillation, where the generative student guides the contrastive student. An encoder-decoder style ReCon-block is proposed that transfers knowledge through cross attention with stop-gradient, which avoids pretraining over-fitting and pattern difference issues. ReCon achieves a new state-of-the-art in 3D representation learning, e.g., 91.26% accuracy on ScanObjectNN. Codes have been released at https://github.com/qizekun/ReCon.

Chengliang Zhong, Yuhang Zheng, Yupeng Zheng et al.

Keypoint-based representation has proven advantageous in various visual and robotic tasks. However, the existing 2D and 3D methods for detecting keypoints mainly rely on geometric consistency to achieve spatial alignment, neglecting temporal consistency. To address this issue, the Transporter method was introduced for 2D data, which reconstructs the target frame from the source frame to incorporate both spatial and temporal information. However, the direct application of the Transporter to 3D point clouds is infeasible due to their structural differences from 2D images. Thus, we propose the first 3D version of the Transporter, which leverages hybrid 3D representation, cross attention, and implicit reconstruction. We apply this new learning system on 3D articulated objects and nonrigid animals (humans and rodents) and show that learned keypoints are spatio-temporally consistent. Additionally, we propose a closed-loop control strategy that utilizes the learned keypoints for 3D object manipulation and demonstrate its superior performance. Codes are available at https://github.com/zhongcl-thu/3D-Implicit-Transporter.

Yunze Liu, Yun Liu, Che Jiang et al.

We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction. HOI4D consists of 2.4M RGB-D egocentric video frames over 4000 sequences collected by 4 participants interacting with 800 different object instances from 16 categories over 610 different indoor rooms. Frame-wise annotations for panoptic segmentation, motion segmentation, 3D hand pose, category-level object pose and hand action have also been provided, together with reconstructed object meshes and scene point clouds. With HOI4D, we establish three benchmarking tasks to promote category-level HOI from 4D visual signals including semantic segmentation of 4D dynamic point cloud sequences, category-level object pose tracking, and egocentric action segmentation with diverse interaction targets. In-depth analysis shows HOI4D poses great challenges to existing methods and produces great research opportunities.

Changfeng Yu, Yi Chang, Yi Li et al.

The deep convolutional neural network has achieved significant progress for single image rain streak removal. However, most of the data-driven learning methods are full-supervised or semi-supervised, unexpectedly suffering from significant performance drops when dealing with real rain. These data-driven learning methods are representative yet generalize poor for real rain. The opposite holds true for the model-driven unsupervised optimization methods. To overcome these problems, we propose a unified unsupervised learning framework which inherits the generalization and representation merits for real rain removal. Specifically, we first discover a simple yet important domain knowledge that directional rain streak is anisotropic while the natural clean image is isotropic, and formulate the structural discrepancy into the energy function of the optimization model. Consequently, we design an optimization model-driven deep CNN in which the unsupervised loss function of the optimization model is enforced on the proposed network for better generalization. In addition, the architecture of the network mimics the main role of the optimization models with better feature representation. On one hand, we take advantage of the deep network to improve the representation. On the other hand, we utilize the unsupervised loss of the optimization model for better generalization. Overall, the unsupervised learning framework achieves good generalization and representation: unsupervised training (loss) with only a few real rainy images (input) and physical meaning network (architecture). Extensive experiments on synthetic and real-world rain datasets show the superiority of the proposed method.

Xueyi Liu, Ji Zhang, Ruizhen Hu et al.

Category-level articulated object pose estimation aims to estimate a hierarchy of articulation-aware object poses of an unseen articulated object from a known category. To reduce the heavy annotations needed for supervised learning methods, we present a novel self-supervised strategy that solves this problem without any human labels. Our key idea is to factorize canonical shapes and articulated object poses from input articulated shapes through part-level equivariant shape analysis. Specifically, we first introduce the concept of part-level SE(3) equivariance and devise a network to learn features of such property. Then, through a carefully designed fine-grained pose-shape disentanglement strategy, we expect that canonical spaces to support pose estimation could be induced automatically. Thus, we could further predict articulated object poses as per-part rigid transformations describing how parts transform from their canonical part spaces to the camera space. Extensive experiments demonstrate the effectiveness of our method on both complete and partial point clouds from synthetic and real articulated object datasets.

Hao Wen, Yunze Liu, Jingwei Huang et al.

This paper proposes a 4D backbone for long-term point cloud video understanding. A typical way to capture spatial-temporal context is using 4Dconv or transformer without hierarchy. However, those methods are neither effective nor efficient enough due to camera motion, scene changes, sampling patterns, and the complexity of 4D data. To address those issues, we leverage the primitive plane as a mid-level representation to capture the long-term spatial-temporal context in 4D point cloud videos and propose a novel hierarchical backbone named Point Primitive Transformer(PPTr), which is mainly composed of intra-primitive point transformers and primitive transformers. Extensive experiments show that PPTr outperforms the previous state of the arts on different tasks.

Zhuoyang Zhang, Yuhao Dong, Yunze Liu et al.

Recent work on 4D point cloud sequences has attracted a lot of attention. However, obtaining exhaustively labeled 4D datasets is often very expensive and laborious, so it is especially important to investigate how to utilize raw unlabeled data. However, most existing self-supervised point cloud representation learning methods only consider geometry from a static snapshot omitting the fact that sequential observations of dynamic scenes could reveal more comprehensive geometric details. And the video representation learning frameworks mostly model motion as image space flows, let alone being 3D-geometric-aware. To overcome such issues, this paper proposes a new 4D self-supervised pre-training method called Complete-to-Partial 4D Distillation. Our key idea is to formulate 4D self-supervised representation learning as a teacher-student knowledge distillation framework and let the student learn useful 4D representations with the guidance of the teacher. Experiments show that this approach significantly outperforms previous pre-training approaches on a wide range of 4D point cloud sequence understanding tasks including indoor and outdoor scenarios.

Yi Li, Hualiang Wang, Yiqun Duan et al.

Contrastive Language-Image Pre-training (CLIP) learns rich representations via readily available supervision of natural language. It improves the performance of downstream vision tasks, including but not limited to the zero-shot, long tail, segmentation, retrieval, caption, and video. However, the visual explainability of CLIP is rarely studied, especially for the raw feature map. To provide visual explanations of its predictions, we propose the Image-Text Similarity Map (ITSM). Based on it, we surprisingly find that CLIP prefers the background regions than the foregrounds, and shows erroneous visualization results against human understanding. This phenomenon is universal for both vision transformers and convolutional networks, which suggests this problem is unique and not owing to certain network. Experimentally, we find the devil is in the pooling part, where inappropriate pooling methods lead to a phenomenon called semantic shift. For this problem, we propose the Explainable Contrastive Language-Image Pre-training (ECLIP), which corrects the explainability via the Masked Max Pooling. Specifically, to avoid the semantic shift, we replace the original attention pooling by max pooling to focus on the confident foreground, with guidance from free attention during training. Experiments on three datasets suggest that ECLIP greatly improves the explainability of CLIP, and beyond previous explainability methods at large margins. The code will be released later.

Yi Li, Huifeng Yao, Hualiang Wang et al.

Fully supervised semantic segmentation learns from dense masks, which requires heavy annotation cost for closed set. In this paper, we use natural language as supervision without any pixel-level annotation for open world segmentation. We call the proposed framework as FreeSeg, where the mask is freely available from raw feature map of pretraining model. Compared with zero-shot or openset segmentation, FreeSeg doesn't require any annotated masks, and it widely predicts categories beyond class-agnostic unsupervised segmentation. Specifically, FreeSeg obtains free mask from Image-Text Similarity Map (ITSM) of Interpretable Contrastive Language-Image Pretraining (ICLIP). And our core improvements are the smoothed min pooling for dense ICLIP, with the partial label and pixel strategies for segmentation. Furthermore, FreeSeg is very straight forward without complex design like grouping, clustering or retrieval. Besides the simplicity, the performances of FreeSeg surpass previous state-of-the-art at large margins, e.g. 13.4% higher at mIoU on VOC dataset in the same settings.

Yun Guo, Xueyao Xiao, Xiaoxiong Wang et al.

In this technical report, we briefly introduce the solution of our team HUST\li VIE for GT-Rain Challenge in CVPR 2023 UG$^{2}$+ Track 3. In this task, we propose an efficient two-stage framework to reconstruct a clear image from rainy frames. Firstly, a low-rank based video deraining method is utilized to generate pseudo GT, which fully takes the advantage of multi and aligned rainy frames. Secondly, a transformer-based single image deraining network Uformer is implemented to pre-train on large real rain dataset and then fine-tuned on pseudo GT to further improve image restoration. Moreover, in terms of visual pleasing effect, a comprehensive image processor module is utilized at the end of pipeline. Our overall framework is elaborately designed and able to handle both heavy rainy and foggy sequences provided in the final testing phase. Finally, we rank 1st on the average structural similarity (SSIM) and rank 2nd on the average peak signal-to-noise ratio (PSNR). Our code is available at https://github.com/yunguo224/UG2_Deraining.

Yi Li, Zhanghui Kuang, Yimin Chen et al.

Successful visual recognition networks benefit from aggregating information spanning from a wide range of scales. Previous research has investigated information fusion of connected layers or multiple branches in a block, seeking to strengthen the power of multi-scale representations. Despite their great successes, existing practices often allocate the neurons for each scale manually, and keep the same ratio in all aggregation blocks of an entire network, rendering suboptimal performance. In this paper, we propose to learn the neuron allocation for aggregating multi-scale information in different building blocks of a deep network. The most informative output neurons in each block are preserved while others are discarded, and thus neurons for multiple scales are competitively and adaptively allocated. Our scale aggregation network (ScaleNet) is constructed by repeating a scale aggregation (SA) block that concatenates feature maps at a wide range of scales. Feature maps for each scale are generated by a stack of downsampling, convolution and upsampling operations. The data-driven neuron allocation and SA block achieve strong representational power at the cost of considerably low computational complexity. The proposed ScaleNet, by replacing all 3x3 convolutions in ResNet with our SA blocks, achieves better performance than ResNet and its outstanding variants like ResNeXt and SE-ResNet, in the same computational complexity. On ImageNet classification, ScaleNets absolutely reduce the top-1 error rate of ResNets by 1.12 (101 layers) and 1.82 (50 layers). On COCO object detection, ScaleNets absolutely improve the mmAP with backbone of ResNets by 3.6 (101 layers) and 4.6 (50 layers) on Faster RCNN, respectively. Code and models are released at https://github.com/Eli-YiLi/ScaleNet.

Yi Li, Haozhi Qi, Jifeng Dai et al.

We present the first fully convolutional end-to-end solution for instance-aware semantic segmentation task. It inherits all the merits of FCNs for semantic segmentation and instance mask proposal. It performs instance mask prediction and classification jointly. The underlying convolutional representation is fully shared between the two sub-tasks, as well as between all regions of interest. The proposed network is highly integrated and achieves state-of-the-art performance in both accuracy and efficiency. It wins the COCO 2016 segmentation competition by a large margin. Code would be released at \url{https://github.com/daijifeng001/TA-FCN}.

Zijian Zhang, Kaiyuan Zheng, Zhaorun Chen et al.

Despite the recent advancements of vision-language-action (VLA) models on a variety of robotics tasks, they suffer from critical issues such as poor generalizability to unseen tasks, due to their reliance on behavior cloning exclusively from successful rollouts. Furthermore, they are typically fine-tuned to replicate demonstrations collected by experts under different settings, thus introducing distribution bias and limiting their adaptability to diverse manipulation objectives, such as efficiency, safety, and task completion. To bridge this gap, we introduce GRAPE: Generalizing Robot Policy via Preference Alignment. Specifically, GRAPE aligns VLAs on a trajectory level and implicitly models reward from both successful and failure trials to boost generalizability to diverse tasks. Moreover, GRAPE breaks down complex manipulation tasks to independent stages and automatically guides preference modeling through customized spatiotemporal constraints with keypoints proposed by a large vision-language model. Notably, these constraints are flexible and can be customized to align the model with varying objectives, such as safety, efficiency, or task success. We evaluate GRAPE across a diverse array of tasks in both real-world and simulated environments. Experimental results demonstrate that GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 58.20%, respectively. Additionally, GRAPE can be aligned with various objectives, such as safety and efficiency, reducing collision rates by 37.44% and rollout step-length by 11.15%, respectively. All code, models, and data are available at https://grape-vla.github.io/

Fei Song, Yi Li, Rui Wang et al.

Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely based on unlabeled test data may induce prompt optimization bias, ultimately leading to suboptimal performance on downstream tasks. In this work, we analyze the underlying causes of prompt optimization bias from both the model and data perspectives. In terms of the model, the entropy minimization objective typically focuses on reducing the entropy of model predictions while overlooking their correctness. This can result in overconfident yet incorrect outputs, thereby compromising the quality of prompt optimization. On the data side, prompts affected by optimization bias can introduce misalignment between visual and textual modalities, which further aggravates the prompt optimization bias. To this end, we propose a Doubly Debiased Test-Time Prompt Tuning method. Specifically, we first introduce a dynamic retrieval-augmented modulation module that retrieves high-confidence knowledge from a dynamic knowledge base using the test image feature as a query, and uses the retrieved knowledge to modulate the predictions. Guided by the refined predictions, we further develop a reliability-aware prompt optimization module that incorporates a confidence-based weighted ensemble and cross-modal consistency distillation to impose regularization constraints during prompt tuning. Extensive experiments across 15 benchmark datasets involving both natural distribution shifts and cross-datasets generalization demonstrate that our method outperforms baselines, validating its effectiveness in mitigating prompt optimization bias.

Yi Li, Xiaoxiong Wang, Jiawei Wang et al.

While image dehazing has advanced substantially in the past decade, most efforts have focused on short-range scenarios, leaving long-range haze removal under-explored. As distance increases, intensified scattering leads to severe haze and signal loss, making it impractical to recover distant details solely from visible images. Near-infrared, with superior fog penetration, offers critical complementary cues through multimodal fusion. However, existing methods focus on content integration while often neglecting haze embedded in visible images, leading to results with residual haze. In this work, we argue that the infrared and visible modalities not only provide complementary low-level visual features, but also share high-level semantic consistency. Motivated by this, we propose a Hierarchical Semantic-Visual Fusion (HSVF) framework, comprising a semantic stream to reconstruct haze-free scenes and a visual stream to incorporate structural details from the near-infrared modality. The semantic stream first acquires haze-robust semantic prediction by aligning modality-invariant intrinsic representations. Then the shared semantics act as strong priors to restore clear and high-contrast distant scenes under severe haze degradation. In parallel, the visual stream focuses on recovering lost structural details from near-infrared by fusing complementary cues from both visible and near-infrared images. Through the cooperation of dual streams, HSVF produces results that exhibit both high-contrast scenes and rich texture details. Moreover, we introduce a novel pixel-aligned visible-infrared haze dataset with semantic labels to facilitate benchmarking. Extensive experiments demonstrate the superiority of our method over state-of-the-art approaches in real-world long-range haze removal.

Yi Li, Xin Xie, Lina Lei et al.

The generation of smooth and continuous images between domains has recently drawn much attention in image-to-image (I2I) translation. Linear relationship acts as the basic assumption in most existing approaches, while applied to different aspects including features, models or labels. However, the linear assumption is hard to conform with the element dimension increases and suffers from the limit that having to obtain both ends of the line. In this paper, we propose a novel rotation-oriented solution and model the continuous generation with an in-plane rotation over the style representation of an image, achieving a network named RoNet. A rotation module is implanted in the generation network to automatically learn the proper plane while disentangling the content and the style of an image. To encourage realistic texture, we also design a patch-based semantic style loss that learns the different styles of the similar object in different domains. We conduct experiments on forest scenes (where the complex texture makes the generation very challenging), faces, streetscapes and the iphone2dslr task. The results validate the superiority of our method in terms of visual quality and continuity.

Yun Liu, Haolin Yang, Xu Si et al.

Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities. However, existing technical approaches for analyzing and synthesizing hand-object manipulation are mostly limited to handling a single hand and object due to the lack of data support. To address this, we construct TACO, an extensive bimanual hand-object-interaction dataset spanning a large variety of tool-action-object compositions for daily human activities. TACO contains 2.5K motion sequences paired with third-person and egocentric views, precise hand-object 3D meshes, and action labels. To rapidly expand the data scale, we present a fully automatic data acquisition pipeline combining multi-view sensing with an optical motion capture system. With the vast research fields provided by TACO, we benchmark three generalizable hand-object-interaction tasks: compositional action recognition, generalizable hand-object motion forecasting, and cooperative grasp synthesis. Extensive experiments reveal new insights, challenges, and opportunities for advancing the studies of generalizable hand-object motion analysis and synthesis. Our data and code are available at https://taco2024.github.io.

Kai Ye, Siyan Dong, Qingnan Fan et al.

We study the problem of multi-robot active mapping, which aims for complete scene map construction in minimum time steps. The key to this problem lies in the goal position estimation to enable more efficient robot movements. Previous approaches either choose the frontier as the goal position via a myopic solution that hinders the time efficiency, or maximize the long-term value via reinforcement learning to directly regress the goal position, but does not guarantee the complete map construction. In this paper, we propose a novel algorithm, namely NeuralCoMapping, which takes advantage of both approaches. We reduce the problem to bipartite graph matching, which establishes the node correspondences between two graphs, denoting robots and frontiers. We introduce a multiplex graph neural network (mGNN) that learns the neural distance to fill the affinity matrix for more effective graph matching. We optimize the mGNN with a differentiable linear assignment layer by maximizing the long-term values that favor time efficiency and map completeness via reinforcement learning. We compare our algorithm with several state-of-the-art multi-robot active mapping approaches and adapted reinforcement-learning baselines. Experimental results demonstrate the superior performance and exceptional generalization ability of our algorithm on various indoor scenes and unseen number of robots, when only trained with 9 indoor scenes.

Zhirui Dai, Yuepeng Jiang, Yi Li et al.

Social distancing, an essential public health measure to limit the spread of contagious diseases, has gained significant attention since the outbreak of the COVID-19 pandemic. In this work, the problem of visual social distancing compliance assessment in busy public areas, with wide field-of-view cameras, is considered. A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed. A multi-branch network, BEV-Net, is proposed to localize individuals in world coordinates and identify high-risk regions where social distancing is violated. BEV-Net combines detection of head and feet locations, camera pose estimation, a differentiable homography module to map image into BEV coordinates, and geometric reasoning to produce a BEV map of the people locations in the scene. Experiments on complex crowded scenes demonstrate the power of the approach and show superior performance over baselines derived from methods in the literature. Applications of interest for public health decision makers are finally discussed. Datasets, code and pretrained models are publicly available at GitHub.

Siyan Dong, Qingnan Fan, He Wang et al.

Localizing the camera in a known indoor environment is a key building block for scene mapping, robot navigation, AR, etc. Recent advances estimate the camera pose via optimization over the 2D/3D-3D correspondences established between the coordinates in 2D/3D camera space and 3D world space. Such a mapping is estimated with either a convolution neural network or a decision tree using only the static input image sequence, which makes these approaches vulnerable to dynamic indoor environments that are quite common yet challenging in the real world. To address the aforementioned issues, in this paper, we propose a novel outlier-aware neural tree which bridges the two worlds, deep learning and decision tree approaches. It builds on three important blocks: (a) a hierarchical space partition over the indoor scene to construct the decision tree; (b) a neural routing function, implemented as a deep classification network, employed for better 3D scene understanding; and (c) an outlier rejection module used to filter out dynamic points during the hierarchical routing process. Our proposed algorithm is evaluated on the RIO-10 benchmark developed for camera relocalization in dynamic indoor environments. It achieves robust neural routing through space partitions and outperforms the state-of-the-art approaches by around 30% on camera pose accuracy, while running comparably fast for evaluation.

Fanbo Xiang, Yuzhe Qin, Kaichun Mo et al.

Building home assistant robots has long been a pursuit for vision and robotics researchers. To achieve this task, a simulated environment with physically realistic simulation, sufficient articulated objects, and transferability to the real robot is indispensable. Existing environments achieve these requirements for robotics simulation with different levels of simplification and focus. We take one step further in constructing an environment that supports household tasks for training robot learning algorithm. Our work, SAPIEN, is a realistic and physics-rich simulated environment that hosts a large-scale set for articulated objects. Our SAPIEN enables various robotic vision and interaction tasks that require detailed part-level understanding.We evaluate state-of-the-art vision algorithms for part detection and motion attribute recognition as well as demonstrate robotic interaction tasks using heuristic approaches and reinforcement learning algorithms. We hope that our SAPIEN can open a lot of research directions yet to be explored, including learning cognition through interaction, part motion discovery, and construction of robotics-ready simulated game environment.

Jie Cao, Huaibo Huang, Yi Li et al.

The performance of multi-domain image-to-image translation has been significantly improved by recent progress in deep generative models. Existing approaches can use a unified model to achieve translations between all the visual domains. However, their outcomes are far from satisfying when there are large domain variations. In this paper, we reveal that improving the sample selection strategy is an effective solution. To select informative samples, we dynamically estimate sample importance during the training of Generative Adversarial Networks, presenting Informative Sample Mining Network. We theoretically analyze the relationship between the sample importance and the prediction of the global optimal discriminator. Then a practical importance estimation function for general conditions is derived. Furthermore, we propose a novel multi-stage sample training scheme to reduce sample hardness while preserving sample informativeness. Extensive experiments on a wide range of specific image-to-image translation tasks are conducted, and the results demonstrate our superiority over current state-of-the-art methods.

Xiaolong Li, He Wang, Li Yi et al.

This project addresses the task of category-level pose estimation for articulated objects from a single depth image. We present a novel category-level approach that correctly accommodates object instances previously unseen during training. We introduce Articulation-aware Normalized Coordinate Space Hierarchy (ANCSH) - a canonical representation for different articulated objects in a given category. As the key to achieve intra-category generalization, the representation constructs a canonical object space as well as a set of canonical part spaces. The canonical object space normalizes the object orientation,scales and articulations (e.g. joint parameters and states) while each canonical part space further normalizes its part pose and scale. We develop a deep network based on PointNet++ that predicts ANCSH from a single depth point cloud, including part segmentation, normalized coordinates, and joint parameters in the canonical object space. By leveraging the canonicalized joints, we demonstrate: 1) improved performance in part pose and scale estimations using the induced kinematic constraints from joints; 2) high accuracy for joint parameter estimation in camera space.

Jie Cao, Huaibo Huang, Yi Li et al.

Despite that the performance of image-to-image translation has been significantly improved by recent progress in generative models, current methods still suffer from severe degradation in training stability and sample quality when applied to the high-resolution situation. In this work, we present a novel training framework for GANs, namely biphasic learning, to achieve image-to-image translation in multiple visual domains at $1024^2$ resolution. Our core idea is to design an adjustable objective function that varies across training phases. Within the biphasic learning framework, we propose a novel inherited adversarial loss to achieve the enhancement of model capacity and stabilize the training phase transition. Furthermore, we introduce a perceptual-level consistency loss through mutual information estimation and maximization. To verify the superiority of the proposed method, we apply it to a wide range of face-related synthesis tasks and conduct experiments on multiple large-scale datasets. Through comprehensive quantitative analyses, we demonstrate that our method significantly outperforms existing methods.

Tong He, Haibin Huang, Li Yi et al.

Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling. However, such connectivity information is lost in point clouds. Thus we introduce GeoNet, the first deep learning architecture trained to model the intrinsic structure of surfaces represented as point clouds. To demonstrate the applicability of learned geodesic-aware representations, we propose fusion schemes which use GeoNet in conjunction with other baseline or backbone networks, such as PU-Net and PointNet++, for down-stream point cloud analysis. Our method improves the state-of-the-art on multiple representative tasks that can benefit from understandings of the underlying surface topology, including point upsampling, normal estimation, mesh reconstruction and non-rigid shape classification.

Xin Zheng, Yanqing Guo, Huaibo Huang et al.

Facial attribute analysis has received considerable attention when deep learning techniques made remarkable breakthroughs in this field over the past few years. Deep learning based facial attribute analysis consists of two basic sub-issues: facial attribute estimation (FAE), which recognizes whether facial attributes are present in given images, and facial attribute manipulation (FAM), which synthesizes or removes desired facial attributes. In this paper, we provide a comprehensive survey of deep facial attribute analysis from the perspectives of both estimation and manipulation. First, we summarize a general pipeline that deep facial attribute analysis follows, which comprises two stages: data preprocessing and model construction. Additionally, we introduce the underlying theories of this two-stage pipeline for both FAE and FAM. Second, the datasets and performance metrics commonly used in facial attribute analysis are presented. Third, we create a taxonomy of state-of-the-art methods and review deep FAE and FAM algorithms in detail. Furthermore, several additional facial attribute related issues are introduced, as well as relevant real-world applications. Finally, we discuss possible challenges and promising future research directions.

Bo Fu, Xiao-Yang Zhao, Yi Li et al.

The salt and pepper noise, especially the one with extremely high percentage of impulses, brings a significant challenge to image denoising. In this paper, we propose a non-local switching filter convolutional neural network denoising algorithm, named NLSF-CNN, for salt and pepper noise. As its name suggested, our NLSF-CNN consists of two steps, i.e., a NLSF processing step and a CNN training step. First, we develop a NLSF pre-processing step for noisy images using non-local information. Then, the pre-processed images are divided into patches and used for CNN training, leading to a CNN denoising model for future noisy images. We conduct a number of experiments to evaluate the effectiveness of NLSF-CNN. Experimental results show that NLSF-CNN outperforms the state-of-the-art denoising algorithms with a few training images.

Yi Li, Lingxiao Song, Xiang Wu et al.

Makeup is widely used to improve facial attractiveness and is well accepted by the public. However, different makeup styles will result in significant facial appearance changes. It remains a challenging problem to match makeup and non-makeup face images. This paper proposes a learning from generation approach for makeup-invariant face verification by introducing a bi-level adversarial network (BLAN). To alleviate the negative effects from makeup, we first generate non-makeup images from makeup ones, and then use the synthesized non-makeup images for further verification. Two adversarial networks in BLAN are integrated in an end-to-end deep network, with the one on pixel level for reconstructing appealing facial images and the other on feature level for preserving identity information. These two networks jointly reduce the sensing gap between makeup and non-makeup images. Moreover, we make the generator well constrained by incorporating multiple perceptual losses. Experimental results on three benchmark makeup face datasets demonstrate that our method achieves state-of-the-art verification accuracy across makeup status and can produce photo-realistic non-makeup face images.

Jifeng Dai, Kaiming He, Yi Li et al.

Fully convolutional networks (FCNs) have been proven very successful for semantic segmentation, but the FCN outputs are unaware of object instances. In this paper, we develop FCNs that are capable of proposing instance-level segment candidates. In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances. On top of these instance-sensitive score maps, a simple assembling module is able to output instance candidate at each position. In contrast to the recent DeepMask method for segmenting instances, our method does not have any high-dimensional layer related to the mask resolution, but instead exploits image local coherence for estimating instances. We present competitive results of instance segment proposal on both PASCAL VOC and MS COCO.

Yezhou Yang, Yi Li, Cornelia Fermuller et al.

In this paper we consider the problem of continuously discovering image contents by actively asking image based questions and subsequently answering the questions being asked. The key components include a Visual Question Generation (VQG) module and a Visual Question Answering module, in which Recurrent Neural Networks (RNN) and Convolutional Neural Network (CNN) are used. Given a dataset that contains images, questions and their answers, both modules are trained at the same time, with the difference being VQG uses the images as input and the corresponding questions as output, while VQA uses images and questions as input and the corresponding answers as output. We evaluate the self talk process subjectively using Amazon Mechanical Turk, which show effectiveness of the proposed method.

Fang Wang, Yi Li

Simple tree models for articulated objects prevails in the last decade. However, it is also believed that these simple tree models are not capable of capturing large variations in many scenarios, such as human pose estimation. This paper attempts to address three questions: 1) are simple tree models sufficient? more specifically, 2) how to use tree models effectively in human pose estimation? and 3) how shall we use combined parts together with single parts efficiently? Assuming we have a set of single parts and combined parts, and the goal is to estimate a joint distribution of their locations. We surprisingly find that no latent variables are introduced in the Leeds Sport Dataset (LSP) during learning latent trees for deformable model, which aims at approximating the joint distributions of body part locations using minimal tree structure. This suggests one can straightforwardly use a mixed representation of single and combined parts to approximate their joint distribution in a simple tree model. As such, one only needs to build Visual Categories of the combined parts, and then perform inference on the learned latent tree. Our method outperformed the state of the art on the LSP, both in the scenarios when the training images are from the same dataset and from the PARSE dataset. Experiments on animal images from the VOC challenge further support our findings.

Fang Wang, Yi Li

Parsing human poses in images is fundamental in extracting critical visual information for artificial intelligent agents. Our goal is to learn self-contained body part representations from images, which we call visual symbols, and their symbol-wise geometric contexts in this parsing process. Each symbol is individually learned by categorizing visual features leveraged by geometric information. In the categorization, we use Latent Support Vector Machine followed by an efficient cross validation procedure to learn visual symbols. Then, these symbols naturally define geometric contexts of body parts in a fine granularity. When the structure of the compositional parts is a tree, we derive an efficient approach to estimating human poses in images. Experiments on two large datasets suggest our approach outperforms state of the art methods.