Kun Li

Wing-Yin Yu, Lai-Man Po, Ray C. C. Cheung et al.

Video-based human pose transfer is a video-to-video generation task that animates a plain source human image based on a series of target human poses. Considering the difficulties in transferring highly structural patterns on the garments and discontinuous poses, existing methods often generate unsatisfactory results such as distorted textures and flickering artifacts. To address these issues, we propose a novel Deformable Motion Modulation (DMM) that utilizes geometric kernel offset with adaptive weight modulation to simultaneously perform feature alignment and style transfer. Different from normal style modulation used in style transfer, the proposed modulation mechanism adaptively reconstructs smoothed frames from style codes according to the object shape through an irregular receptive field of view. To enhance the spatio-temporal consistency, we leverage bidirectional propagation to extract the hidden motion information from a warped image sequence generated by noisy poses. The proposed feature propagation significantly enhances the motion prediction ability by forward and backward propagation. Both quantitative and qualitative experimental results demonstrate superiority over the state-of-the-arts in terms of image fidelity and visual continuity. The source code is publicly available at github.com/rocketappslab/bdmm.

Yu Wang, Shuhui Bu, Lin Chen et al.

Recently, cross-source point cloud registration from different sensors has become a significant research focus. However, traditional methods confront challenges due to the varying density and structure of cross-source point clouds. In order to solve these problems, we propose a cross-source point cloud fusion algorithm called HybridFusion. It can register cross-source dense point clouds from different viewing angle in outdoor large scenes. The entire registration process is a coarse-to-fine procedure. First, the point cloud is divided into small patches, and a matching patch set is selected based on global descriptors and spatial distribution, which constitutes the coarse matching process. To achieve fine matching, 2D registration is performed by extracting 2D boundary points from patches, followed by 3D adjustment. Finally, the results of multiple patch pose estimates are clustered and fused to determine the final pose. The proposed approach is evaluated comprehensively through qualitative and quantitative experiments. In order to compare the robustness of cross-source point cloud registration, the proposed method and generalized iterative closest point method are compared. Furthermore, a metric for describing the degree of point cloud filling is proposed. The experimental results demonstrate that our approach achieves state-of-the-art performance in cross-source point cloud registration.

Kun Li, Dan Guo, Guoliang Chen et al.

In this paper, we briefly introduce the solution of our team HFUT-VUT for the Micros-gesture Classification in the MiGA challenge at IJCAI 2023. The micro-gesture classification task aims at recognizing the action category of a given video based on the skeleton data. For this task, we propose a 3D-CNNs-based micro-gesture recognition network, which incorporates a skeletal and semantic embedding loss to improve action classification performance. Finally, we rank 1st in the Micro-gesture Classification Challenge, surpassing the second-place team in terms of Top-1 accuracy by 1.10%.

Jinsong Zhang, Minjie Zhu, Yuxiang Zhang et al.

This paper addresses the problem of generating whole-body motion from speech. Despite great successes, prior methods still struggle to produce reasonable and diverse whole-body motions from speech. This is due to their reliance on suboptimal representations and a lack of strategies for generating diverse results. To address these challenges, we present a novel hybrid point representation to achieve accurate and continuous motion generation, e.g., avoiding foot skating, and this representation can be transformed into an easy-to-use representation, i.e., SMPL-X body mesh, for many applications. To generate whole-body motion from speech, for facial motion, closely tied to the audio signal, we introduce an encoder-decoder architecture to achieve deterministic outcomes. However, for the body and hands, which have weaker connections to the audio signal, we aim to generate diverse yet reasonable motions. To boost diversity in motion generation, we propose a contrastive motion learning method to encourage the model to produce more distinctive representations. Specifically, we design a robust VQ-VAE to learn a quantized motion codebook using our hybrid representation. Then, we regress the motion representation from the audio signal by a translation model employing our contrastive motion learning method. Experimental results validate the superior performance and the correctness of our model. The project page is available for research purposes at http://cic.tju.edu.cn/faculty/likun/projects/SpeechAct.

Xiongzheng Li, Jinsong Zhang, Yu-Kun Lai et al.

Much progress has been made in reconstructing garments from an image or a video. However, none of existing works meet the expectations of digitizing high-quality animatable dynamic garments that can be adjusted to various unseen poses. In this paper, we propose the first method to recover high-quality animatable dynamic garments from monocular videos without depending on scanned data. To generate reasonable deformations for various unseen poses, we propose a learnable garment deformation network that formulates the garment reconstruction task as a pose-driven deformation problem. To alleviate the ambiguity estimating 3D garments from monocular videos, we design a multi-hypothesis deformation module that learns spatial representations of multiple plausible deformations. Experimental results on several public datasets demonstrate that our method can reconstruct high-quality dynamic garments with coherent surface details, which can be easily animated under unseen poses. The code will be provided for research purposes.

Jingjing Hu, Dan Guo, Kun Li et al.

Inspired by the activity-silent and persistent activity mechanisms in human visual perception biology, we design a Unified Static and Dynamic Network (UniSDNet), to learn the semantic association between the video and text/audio queries in a cross-modal environment for efficient video grounding. For static modeling, we devise a novel residual structure (ResMLP) to boost the global comprehensive interaction between the video segments and queries, achieving more effective semantic enhancement/supplement. For dynamic modeling, we effectively exploit three characteristics of the persistent activity mechanism in our network design for a better video context comprehension. Specifically, we construct a diffusely connected video clip graph on the basis of 2D sparse temporal masking to reflect the "short-term effect" relationship. We innovatively consider the temporal distance and relevance as the joint "auxiliary evidence clues" and design a multi-kernel Temporal Gaussian Filter to expand the context clue into high-dimensional space, simulating the "complex visual perception", and then conduct element level filtering convolution operations on neighbour clip nodes in message passing stage for finally generating and ranking the candidate proposals. Our UniSDNet is applicable to both Natural Language Video Grounding (NLVG) and Spoken Language Video Grounding (SLVG) tasks. Our UniSDNet achieves SOTA performance on three widely used datasets for NLVG, as well as three datasets for SLVG, e.g., reporting new records at 38.88% R@1,IoU@0.7 on ActivityNet Captions and 40.26% R@1,IoU@0.5 on TACoS. To facilitate this field, we collect two new datasets (Charades-STA Speech and TACoS Speech) for SLVG task. Meanwhile, the inference speed of our UniSDNet is 1.56$\times$ faster than the strong multi-query benchmark. Code is available at: https://github.com/xian-sh/UniSDNet.

Hao Wen, Jing Huang, Huili Cui et al.

Image-based multi-person reconstruction in wide-field large scenes is critical for crowd analysis and security alert. However, existing methods cannot deal with large scenes containing hundreds of people, which encounter the challenges of large number of people, large variations in human scale, and complex spatial distribution. In this paper, we propose Crowd3D, the first framework to reconstruct the 3D poses, shapes and locations of hundreds of people with global consistency from a single large-scene image. The core of our approach is to convert the problem of complex crowd localization into pixel localization with the help of our newly defined concept, Human-scene Virtual Interaction Point (HVIP). To reconstruct the crowd with global consistency, we propose a progressive reconstruction network based on HVIP by pre-estimating a scene-level camera and a ground plane. To deal with a large number of persons and various human sizes, we also design an adaptive human-centric cropping scheme. Besides, we contribute a benchmark dataset, LargeCrowd, for crowd reconstruction in a large scene. Experimental results demonstrate the effectiveness of the proposed method. The code and datasets will be made public.

Huanjing Yue, Zifan Cui, Kun Li et al.

Dual-lens super-resolution (SR) is a practical scenario for reference (Ref) based SR by utilizing the telephoto image (Ref) to assist the super-resolution of the low-resolution wide-angle image (LR input). Different from general RefSR, the Ref in dual-lens SR only covers the overlapped field of view (FoV) area. However, current dual-lens SR methods rarely utilize these specific characteristics and directly perform dense matching between the LR input and Ref. Due to the resolution gap between LR and Ref, the matching may miss the best-matched candidate and destroy the consistent structures in the overlapped FoV area. Different from them, we propose to first align the Ref with the center region (namely the overlapped FoV area) of the LR input by combining global warping and local warping to make the aligned Ref be sharp and consistent. Then, we formulate the aligned Ref and LR center as value-key pairs, and the corner region of the LR is formulated as queries. In this way, we propose a kernel-free matching strategy by matching between the LR-corner (query) and LR-center (key) regions, and the corresponding aligned Ref (value) can be warped to the corner region of the target. Our kernel-free matching strategy avoids the resolution gap between LR and Ref, which makes our network have better generalization ability. In addition, we construct a DuSR-Real dataset with (LR, Ref, HR) triples, where the LR and HR are well aligned. Experiments on three datasets demonstrate that our method outperforms the second-best method by a large margin. Our code and dataset are available at https://github.com/ZifanCui/KeDuSR.

Kun Li, Lai-Man Po, Hongzheng Yang et al.

Multimodal Large Language Models (MLLMs) are increasingly applied in Personalized Image Aesthetic Assessment (PIAA) as a scalable alternative to expert evaluations. However, their predictions may reflect subtle biases influenced by demographic factors such as gender, age, and education. In this work, we propose AesBiasBench, a benchmark designed to evaluate MLLMs along two complementary dimensions: (1) stereotype bias, quantified by measuring variations in aesthetic evaluations across demographic groups; and (2) alignment between model outputs and genuine human aesthetic preferences. Our benchmark covers three subtasks (Aesthetic Perception, Assessment, Empathy) and introduces structured metrics (IFD, NRD, AAS) to assess both bias and alignment. We evaluate 19 MLLMs, including proprietary models (e.g., GPT-4o, Claude-3.5-Sonnet) and open-source models (e.g., InternVL-2.5, Qwen2.5-VL). Results indicate that smaller models exhibit stronger stereotype biases, whereas larger models align more closely with human preferences. Incorporating identity information often exacerbates bias, particularly in emotional judgments. These findings underscore the importance of identity-aware evaluation frameworks in subjective vision-language tasks.

Hao Liang, Chengjie, Kun Li et al.

Hyperspectral image (HSI) denoising is an essential procedure for HSI applications. Unfortunately, the existing Transformer-based methods mainly focus on non-local modeling, neglecting the importance of locality in image denoising. Moreover, deep learning methods employ complex spectral learning mechanisms, thus introducing large computation costs. To address these problems, we propose a hybrid spatial-spectral denoising network (HSSD), in which we design a novel hybrid dual-path network inspired by CNN and Transformer characteristics, leading to capturing both local and non-local spatial details while suppressing noise efficiently. Furthermore, to reduce computational complexity, we adopt a simple but effective decoupling strategy that disentangles the learning of space and spectral channels, where multilayer perception with few parameters is utilized to learn the global correlations among spectra. The synthetic and real experiments demonstrate that our proposed method outperforms state-of-the-art methods on spatial and spectral reconstruction. The code and details are available on https://github.com/HLImg/HSSD.

Lei Sun, Hang Guo, Bin Ren et al.

This paper presents an overview of the NTIRE 2025 Image Denoising Challenge (σ = 50), highlighting the proposed methodologies and corresponding results. The primary objective is to develop a network architecture capable of achieving high-quality denoising performance, quantitatively evaluated using PSNR, without constraints on computational complexity or model size. The task assumes independent additive white Gaussian noise (AWGN) with a fixed noise level of 50. A total of 290 participants registered for the challenge, with 20 teams successfully submitting valid results, providing insights into the current state-of-the-art in image denoising.

Zhangbin Li, Jinxing Zhou, Jing Zhang et al.

Answering questions related to audio-visual scenes, i.e., the AVQA task, is becoming increasingly popular. A critical challenge is accurately identifying and tracking sounding objects related to the question along the timeline. In this paper, we present a new Patch-level Sounding Object Tracking (PSOT) method. It begins with a Motion-driven Key Patch Tracking (M-KPT) module, which relies on visual motion information to identify salient visual patches with significant movements that are more likely to relate to sounding objects and questions. We measure the patch-wise motion intensity map between neighboring video frames and utilize it to construct and guide a motion-driven graph network. Meanwhile, we design a Sound-driven KPT (S-KPT) module to explicitly track sounding patches. This module also involves a graph network, with the adjacency matrix regularized by the audio-visual correspondence map. The M-KPT and S-KPT modules are performed in parallel for each temporal segment, allowing balanced tracking of salient and sounding objects. Based on the tracked patches, we further propose a Question-driven KPT (Q-KPT) module to retain patches highly relevant to the question, ensuring the model focuses on the most informative clues. The audio-visual-question features are updated during the processing of these modules, which are then aggregated for final answer prediction. Extensive experiments on standard datasets demonstrate the effectiveness of our method, achieving competitive performance even compared to recent large-scale pretraining-based approaches.

Zhiliang Wu, Kerui Chen, Kun Li et al.

Video inpainting aims to fill in corrupted regions of the video with plausible contents. Existing methods generally assume that the locations of corrupted regions are known, focusing primarily on the "how to inpaint". This reliance necessitates manual annotation of the corrupted regions using binary masks to indicate "whereto inpaint". However, the annotation of these masks is labor-intensive and expensive, limiting the practicality of current methods. In this paper, we expect to relax this assumption by defining a new blind video inpainting setting, enabling the networks to learn the mapping from corrupted video to inpainted result directly, eliminating the need of corrupted region annotations. Specifically, we propose an end-to-end blind video inpainting network (BVINet) to address both "where to inpaint" and "how to inpaint" simultaneously. On the one hand, BVINet can predict the masks of corrupted regions by detecting semantic-discontinuous regions of the frame and utilizing temporal consistency prior of the video. On the other hand, the predicted masks are incorporated into the BVINet, allowing it to capture valid context information from uncorrupted regions to fill in corrupted ones. Besides, we introduce a consistency loss to regularize the training parameters of BVINet. In this way, mask prediction and video completion mutually constrain each other, thereby maximizing the overall performance of the trained model. Furthermore, we customize a dataset consisting of synthetic corrupted videos, real-world corrupted videos, and their corresponding completed videos. This dataset serves as a valuable resource for advancing blind video inpainting research. Extensive experimental results demonstrate the effectiveness and superiority of our method.

Muxin Zhang, Qiao Feng, Zhuo Su et al.

3D human generation is increasingly significant in various applications. However, the direct use of 2D generative methods in 3D generation often results in losing local details, while methods that reconstruct geometry from generated images struggle with global view consistency. In this work, we introduce Joint2Human, a novel method that leverages 2D diffusion models to generate detailed 3D human geometry directly, ensuring both global structure and local details. To achieve this, we employ the Fourier occupancy field (FOF) representation, enabling the direct generation of 3D shapes as preliminary results with 2D generative models. With the proposed high-frequency enhancer and the multi-view recarving strategy, our method can seamlessly integrate the details from different views into a uniform global shape. To better utilize the 3D human prior and enhance control over the generated geometry, we introduce a compact spherical embedding of 3D joints. This allows for an effective guidance of pose during the generation process. Additionally, our method can generate 3D humans guided by textual inputs. Our experimental results demonstrate the capability of our method to ensure global structure, local details, high resolution, and low computational cost simultaneously. More results and the code can be found on our project page at http://cic.tju.edu.cn/faculty/likun/projects/Joint2Human.

Pengyu Liu, Kun Li, Fei Wang et al.

In this paper, we introduce the latest solution developed by our team, HFUT-VUT, for the Micro-gesture Online Recognition track of the IJCAI 2025 MiGA Challenge. The Micro-gesture Online Recognition task is a highly challenging problem that aims to locate the temporal positions and recognize the categories of multiple micro-gesture instances in untrimmed videos. Compared to traditional temporal action detection, this task places greater emphasis on distinguishing between micro-gesture categories and precisely identifying the start and end times of each instance. Moreover, micro-gestures are typically spontaneous human actions, with greater differences than those found in other human actions. To address these challenges, we propose hand-crafted data augmentation and spatial-temporal attention to enhance the model's ability to classify and localize micro-gestures more accurately. Our solution achieved an F1 score of 38.03, outperforming the previous state-of-the-art by 37.9%. As a result, our method ranked first in the Micro-gesture Online Recognition track.

Haoyang Ge, Qiao Feng, Hailong Jia et al.

Human pose and shape (HPS) estimation with lensless imaging is not only beneficial to privacy protection but also can be used in covert surveillance scenarios due to the small size and simple structure of this device. However, this task presents significant challenges due to the inherent ambiguity of the captured measurements and lacks effective methods for directly estimating human pose and shape from lensless data. In this paper, we propose the first end-to-end framework to recover 3D human poses and shapes from lensless measurements to our knowledge. We specifically design a multi-scale lensless feature decoder to decode the lensless measurements through the optically encoded mask for efficient feature extraction. We also propose a double-head auxiliary supervision mechanism to improve the estimation accuracy of human limb ends. Besides, we establish a lensless imaging system and verify the effectiveness of our method on various datasets acquired by our lensless imaging system.

Kun Li, George Vosselman, Michael Ying Yang

The goal of referring remote sensing image segmentation (RRSIS) is to extract specific pixel-level regions within an aerial image via a natural language expression. Recent advancements, particularly Transformer-based fusion designs, have demonstrated remarkable progress in this domain. However, existing methods primarily focus on refining visual features using language-aware guidance during the cross-modal fusion stage, neglecting the complementary vision-to-language flow. This limitation often leads to irrelevant or suboptimal representations. In addition, the diverse spatial scales of ground objects in aerial images pose significant challenges to the visual perception capabilities of existing models when conditioned on textual inputs. In this paper, we propose an innovative framework called Scale-wise Bidirectional Alignment Network (SBANet) to address these challenges for RRSIS. Specifically, we design a Bidirectional Alignment Module (BAM) with learnable query tokens to selectively and effectively represent visual and linguistic features, emphasizing regions associated with key tokens. BAM is further enhanced with a dynamic feature selection block, designed to provide both macro- and micro-level visual features, preserving global context and local details to facilitate more effective cross-modal interaction. Furthermore, SBANet incorporates a text-conditioned channel and spatial aggregator to bridge the gap between the encoder and decoder, enhancing cross-scale information exchange in complex aerial scenarios. Extensive experiments demonstrate that our proposed method achieves superior performance in comparison to previous state-of-the-art methods on the RRSIS-D and RefSegRS datasets, both quantitatively and qualitatively. The code will be released after publication.

Hao Wen, Hongbo Kang, Jian Ma et al.

3D reconstruction of dynamic crowds in large scenes has become increasingly important for applications such as city surveillance and crowd analysis. However, current works attempt to reconstruct 3D crowds from a static image, causing a lack of temporal consistency and inability to alleviate the typical impact caused by occlusions. In this paper, we propose DyCrowd, the first framework for spatio-temporally consistent 3D reconstruction of hundreds of individuals' poses, positions and shapes from a large-scene video. We design a coarse-to-fine group-guided motion optimization strategy for occlusion-robust crowd reconstruction in large scenes. To address temporal instability and severe occlusions, we further incorporate a VAE (Variational Autoencoder)-based human motion prior along with a segment-level group-guided optimization. The core of our strategy leverages collective crowd behavior to address long-term dynamic occlusions. By jointly optimizing the motion sequences of individuals with similar motion segments and combining this with the proposed Asynchronous Motion Consistency (AMC) loss, we enable high-quality unoccluded motion segments to guide the motion recovery of occluded ones, ensuring robust and plausible motion recovery even in the presence of temporal desynchronization and rhythmic inconsistencies. Additionally, in order to fill the gap of no existing well-annotated large-scene video dataset, we contribute a virtual benchmark dataset, VirtualCrowd, for evaluating dynamic crowd reconstruction from large-scene videos. Experimental results demonstrate that the proposed method achieves state-of-the-art performance in the large-scene dynamic crowd reconstruction task. The code and dataset will be available for research purposes.

Jing Huang, Hao Wen, Tianyi Zhou et al.

This paper focuses on spatially consistent hundreds of human pose and shape reconstruction from a single large-scene image with various human scales under arbitrary camera FoVs (Fields of View). Due to the small and highly varying 2D human scales, depth ambiguity, and perspective distortion, no existing methods can achieve globally consistent reconstruction with correct reprojection. To address these challenges, we first propose a new concept, Human-scene Virtual Interaction Point (HVIP), to convert the complex 3D human localization into 2D-pixel localization. We then extend it to RCR (Robust Crowd Reconstruction), which achieves globally consistent reconstruction and stable generalization on different camera FoVs without test-time optimization. To perceive humans in varying pixel sizes, we propose an Iterative Ground-aware Cropping to automatically crop the image and then merge the results. To eliminate the influence of the camera and cropping process during the reconstruction, we introduce a canonical Upright 3D Space and the corresponding Upright 2D Space. To link the canonical space and the camera space, we propose the Upright Normalization, which transforms the local crop input into the Upright 2D Space, and transforms the output from the Upright 3D Space into the unified camera space. Besides, we contribute two benchmark datasets, LargeCrowd and SynCrowd, for evaluating crowd reconstruction in large scenes. Experimental results demonstrate the effectiveness of the proposed method. The source code and data will be publicly available for research purposes.

Kun Li, Hao Cheng, George Vosselman et al.

Interactive image segmentation enables users to interact minimally with a machine, facilitating the gradual refinement of the segmentation mask for a target of interest. Previous studies have demonstrated impressive performance in extracting a single target mask through interactive segmentation. However, the information cues of previously interacted objects have been overlooked in the existing methods, which can be further explored to speed up interactive segmentation for multiple targets in the same category. To this end, we introduce novel interactive segmentation frameworks for both a single object and multiple objects in the same category. Specifically, our model leverages transformer backbones to extract interaction-focused visual features from the image and the interactions to obtain a satisfactory mask of a target as an exemplar. For multiple objects, we propose an exemplar-informed module to enhance the learning of similarities among the objects of the target category. To combine attended features from different modules, we incorporate cross-attention blocks followed by a feature fusion module. Experiments conducted on mainstream benchmarks demonstrate that our models achieve superior performance compared to previous methods. Particularly, our model reduces users' labor by around 15\%, requiring two fewer clicks to achieve target IoUs 85\% and 90\%. The results highlight our models' potential as a flexible and practical annotation tool. The source code will be released after publication.

Yuanwang Yang, Qiao Feng, Yu-Kun Lai et al.

Rendering 3D human appearance from a single image in real-time is crucial for achieving holographic communication and immersive VR/AR. Existing methods either rely on multi-camera setups or are constrained to offline operations. In this paper, we propose R2Human, the first approach for real-time inference and rendering of photorealistic 3D human appearance from a single image. The core of our approach is to combine the strengths of implicit texture fields and explicit neural rendering with our novel representation, namely Z-map. Based on this, we present an end-to-end network that performs high-fidelity color reconstruction of visible areas and provides reliable color inference for occluded regions. To further enhance the 3D perception ability of our network, we leverage the Fourier occupancy field as a prior for generating the texture field and providing a sampling surface in the rendering stage. We also propose a consistency loss and a spatial fusion strategy to ensure the multi-view coherence. Experimental results show that our method outperforms the state-of-the-art methods on both synthetic data and challenging real-world images, in real-time. The project page can be found at http://cic.tju.edu.cn/faculty/likun/projects/R2Human.

Jinsong Zhang, Lingfeng Gu, Yu-Kun Lai et al.

Group detection, especially for large-scale scenes, has many potential applications for public safety and smart cities. Existing methods fail to cope with frequent occlusions in large-scale scenes with multiple people, and are difficult to effectively utilize spatio-temporal information. In this paper, we propose an end-to-end framework,GroupTransformer, for group detection in large-scale scenes. To deal with the frequent occlusions caused by multiple people, we design an occlusion encoder to detect and suppress severely occluded person crops. To explore the potential spatio-temporal relationship, we propose spatio-temporal transformers to simultaneously extract trajectory information and fuse inter-person features in a hierarchical manner. Experimental results on both large-scale and small-scale scenes demonstrate that our method achieves better performance compared with state-of-the-art methods. On large-scale scenes, our method significantly boosts the performance in terms of precision and F1 score by more than 10%. On small-scale scenes, our method still improves the performance of F1 score by more than 5%. The project page with code can be found at http://cic.tju.edu.cn/faculty/likun/projects/GroupTrans.

Tiansong Zhou, Jing Huang, Tao Yu et al.

In this paper, we aim to address the challenge of novel view rendering of human performers who wear clothes with complex texture patterns using a sparse set of camera views. Although some recent works have achieved remarkable rendering quality on humans with relatively uniform textures using sparse views, the rendering quality remains limited when dealing with complex texture patterns as they are unable to recover the high-frequency geometry details that are observed in the input views. To this end, we propose HDhuman, which uses a human reconstruction network with a pixel-aligned spatial transformer and a rendering network with geometry-guided pixel-wise feature integration to achieve high-quality human reconstruction and rendering. The designed pixel-aligned spatial transformer calculates the correlations between the input views and generates human reconstruction results with high-frequency details. Based on the surface reconstruction results, the geometry-guided pixel-wise visibility reasoning provides guidance for multi-view feature integration, enabling the rendering network to render high-quality images at 2k resolution on novel views. Unlike previous neural rendering works that always need to train or fine-tune an independent network for a different scene, our method is a general framework that is able to generalize to novel subjects. Experiments show that our approach outperforms all the prior generic or specific methods on both synthetic data and real-world data.

Jinsong Zhang, Kun Li, Yu-Kun Lai et al.

Person image synthesis, e.g., pose transfer, is a challenging problem due to large variation and occlusion. Existing methods have difficulties predicting reasonable invisible regions and fail to decouple the shape and style of clothing, which limits their applications on person image editing. In this paper, we propose PISE, a novel two-stage generative model for Person Image Synthesis and Editing, which is able to generate realistic person images with desired poses, textures, or semantic layouts. For human pose transfer, we first synthesize a human parsing map aligned with the target pose to represent the shape of clothing by a parsing generator, and then generate the final image by an image generator. To decouple the shape and style of clothing, we propose joint global and local per-region encoding and normalization to predict the reasonable style of clothing for invisible regions. We also propose spatial-aware normalization to retain the spatial context relationship in the source image. The results of qualitative and quantitative experiments demonstrate the superiority of our model on human pose transfer. Besides, the results of texture transfer and region editing show that our model can be applied to person image editing.

Kun Li, Jinsong Zhang, Yebin Liu et al.

Human pose transfer, which aims at transferring the appearance of a given person to a target pose, is very challenging and important in many applications. Previous work ignores the guidance of pose features or only uses local attention mechanism, leading to implausible and blurry results. We propose a new human pose transfer method using a generative adversarial network (GAN) with simplified cascaded blocks. In each block, we propose a pose-guided non-local attention (PoNA) mechanism with a long-range dependency scheme to select more important regions of image features to transfer. We also design pre-posed image-guided pose feature update and post-posed pose-guided image feature update to better utilize the pose and image features. Our network is simple, stable, and easy to train. Quantitative and qualitative results on Market-1501 and DeepFashion datasets show the efficacy and efficiency of our model. Compared with state-of-the-art methods, our model generates sharper and more realistic images with rich details, while having fewer parameters and faster speed. Furthermore, our generated images can help to alleviate data insufficiency for person re-identification.

Jinsong Zhang, Xingzi Liu, Kun Li

Human pose transfer, as a misaligned image generation task, is very challenging. Existing methods cannot effectively utilize the input information, which often fail to preserve the style and shape of hair and clothes. In this paper, we propose an adaptive human pose transfer network with two hierarchical deformation levels. The first level generates human semantic parsing aligned with the target pose, and the second level generates the final textured person image in the target pose with the semantic guidance. To avoid the drawback of vanilla convolution that treats all the pixels as valid information, we use gated convolution in both two levels to dynamically select the important features and adaptively deform the image layer by layer. Our model has very few parameters and is fast to converge. Experimental results demonstrate that our model achieves better performance with more consistent hair, face and clothes with fewer parameters than state-of-the-art methods. Furthermore, our method can be applied to clothing texture transfer.

Yuemei Zhou, Gaochang Wu, Ying Fu et al.

Various combinations of cameras enrich computational photography, among which reference-based superresolution (RefSR) plays a critical role in multiscale imaging systems. However, existing RefSR approaches fail to accomplish high-fidelity super-resolution under a large resolution gap, e.g., 8x upscaling, due to the lower consideration of the underlying scene structure. In this paper, we aim to solve the RefSR problem in actual multiscale camera systems inspired by multiplane image (MPI) representation. Specifically, we propose Cross-MPI, an end-to-end RefSR network composed of a novel plane-aware attention-based MPI mechanism, a multiscale guided upsampling module as well as a super-resolution (SR) synthesis and fusion module. Instead of using a direct and exhaustive matching between the cross-scale stereo, the proposed plane-aware attention mechanism fully utilizes the concealed scene structure for efficient attention-based correspondence searching. Further combined with a gentle coarse-to-fine guided upsampling strategy, the proposed Cross-MPI can achieve a robust and accurate detail transmission. Experimental results on both digitally synthesized and optical zoom cross-scale data show that the Cross-MPI framework can achieve superior performance against the existing RefSR methods and is a real fit for actual multiscale camera systems even with large-scale differences.

Kun Li, Jing Yang, Nianhong Jiao et al.

3D face reconstruction from a single image is a challenging problem, especially under partial occlusions and extreme poses. This is because the uncertainty of the estimated 2D landmarks will affect the quality of face reconstruction. In this paper, we propose a novel joint 2D and 3D optimization method to adaptively reconstruct 3D face shapes from a single image, which combines the depths of 3D landmarks to solve the uncertain detections of invisible landmarks. The strategy of our method involves two aspects: a coarse-to-fine pose estimation using both 2D and 3D landmarks, and an adaptive 2D and 3D re-weighting based on the refined pose parameter to recover accurate 3D faces. Experimental results on multiple datasets demonstrate that our method can generate high-quality reconstruction from a single color image and is robust for self-occlusion and large poses.

Jingyu Yang, Ji Xu, Kun Li et al.

This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes. Unlike existing methods that require recording a video using a color camera and/or a depth camera, our method only needs a small number of (e.g., 3-5) color images from uncalibrated sparse views as input, which greatly simplifies data acquisition and extends applicable scenarios. Since different views have limited overlaps, our method allows a single image as input to discern the depth and semantic information of the scene. The key issue is how to recover relatively accurate depth from single images and reconstruct a 3D scene by fusing very few depth maps. To address this problem, we first design an iterative deep architecture, IterNet, that estimates depth and semantic segmentation alternately, so that they benefit each other. To deal with the little overlap and non-rigid transformation between views, we further propose a joint global and local registration method to reconstruct a 3D scene with semantic information from sparse views. We also make available a new indoor synthetic dataset simultaneously providing photorealistic high-resolution RGB images, accurate depth maps and pixel-level semantic labels for thousands of complex layouts, useful for training and evaluation. Experimental results on public datasets and our dataset demonstrate that our method achieves more accurate depth estimation, smaller semantic segmentation errors and better 3D reconstruction results, compared with state-of-the-art methods.

Kun Li, Joel W. Burdick

This work handles the inverse reinforcement learning (IRL) problem where only a small number of demonstrations are available from a demonstrator for each high-dimensional task, insufficient to estimate an accurate reward function. Observing that each demonstrator has an inherent reward for each state and the task-specific behaviors mainly depend on a small number of key states, we propose a meta IRL algorithm that first models the reward function for each task as a distribution conditioned on a baseline reward function shared by all tasks and dependent only on the demonstrator, and then finds the most likely reward function in the distribution that explains the task-specific behaviors. We test the method in a simulated environment on path planning tasks with limited demonstrations, and show that the accuracy of the learned reward function is significantly improved. We also apply the method to analyze the motion of a patient under rehabilitation.

Kun Li, Jingyu Yang, Yu-Kun Lai et al.

Non-rigid registration is challenging because it is ill-posed with high degrees of freedom and is thus sensitive to noise and outliers. We propose a robust non-rigid registration method using reweighted sparsities on position and transformation to estimate the deformations between 3-D shapes. We formulate the energy function with position and transformation sparsity on both the data term and the smoothness term, and define the smoothness constraint using local rigidity. The double sparsity based non-rigid registration model is enhanced with a reweighting scheme, and solved by transferring the model into four alternately-optimized subproblems which have exact solutions and guaranteed convergence. Experimental results on both public datasets and real scanned datasets show that our method outperforms the state-of-the-art methods and is more robust to noise and outliers than conventional non-rigid registration methods.