Yu‐Kun Lai

Ran Yi, Haoyuan Tian, Zhihao Gu et al.

Image aesthetics assessment (IAA) is a challenging task due to its highly subjective nature. Most of the current studies rely on large-scale datasets (e.g., AVA and AADB) to learn a general model for all kinds of photography images. However, little light has been shed on measuring the aesthetic quality of artistic images, and the existing datasets only contain relatively few artworks. Such a defect is a great obstacle to the aesthetic assessment of artistic images. To fill the gap in the field of artistic image aesthetics assessment (AIAA), we first introduce a large-scale AIAA dataset: Boldbrush Artistic Image Dataset (BAID), which consists of 60,337 artistic images covering various art forms, with more than 360,000 votes from online users. We then propose a new method, SAAN (Style-specific Art Assessment Network), which can effectively extract and utilize style-specific and generic aesthetic information to evaluate artistic images. Experiments demonstrate that our proposed approach outperforms existing IAA methods on the proposed BAID dataset according to quantitative comparisons. We believe the proposed dataset and method can serve as a foundation for future AIAA works and inspire more research in this field. Dataset and code are available at: https://github.com/Dreemurr-T/BAID.git

Yu-Jie Yuan, Yang-Tian Sun, Yu-Kun Lai et al.

Implicit neural rendering, especially Neural Radiance Field (NeRF), has shown great potential in novel view synthesis of a scene. However, current NeRF-based methods cannot enable users to perform user-controlled shape deformation in the scene. While existing works have proposed some approaches to modify the radiance field according to the user's constraints, the modification is limited to color editing or object translation and rotation. In this paper, we propose a method that allows users to perform controllable shape deformation on the implicit representation of the scene, and synthesizes the novel view images of the edited scene without re-training the network. Specifically, we establish a correspondence between the extracted explicit mesh representation and the implicit neural representation of the target scene. Users can first utilize well-developed mesh-based deformation methods to deform the mesh representation of the scene. Our method then utilizes user edits from the mesh representation to bend the camera rays by introducing a tetrahedra mesh as a proxy, obtaining the rendering results of the edited scene. Extensive experiments demonstrate that our framework can achieve ideal editing results not only on synthetic data, but also on real scenes captured by users.

Yi-Hua Huang, Yue He, Yu-Jie Yuan et al.

3D scene stylization aims at generating stylized images of the scene from arbitrary novel views following a given set of style examples, while ensuring consistency when rendered from different views. Directly applying methods for image or video stylization to 3D scenes cannot achieve such consistency. Thanks to recently proposed neural radiance fields (NeRF), we are able to represent a 3D scene in a consistent way. Consistent 3D scene stylization can be effectively achieved by stylizing the corresponding NeRF. However, there is a significant domain gap between style examples which are 2D images and NeRF which is an implicit volumetric representation. To address this problem, we propose a novel mutual learning framework for 3D scene stylization that combines a 2D image stylization network and NeRF to fuse the stylization ability of 2D stylization network with the 3D consistency of NeRF. We first pre-train a standard NeRF of the 3D scene to be stylized and replace its color prediction module with a style network to obtain a stylized NeRF. It is followed by distilling the prior knowledge of spatial consistency from NeRF to the 2D stylization network through an introduced consistency loss. We also introduce a mimic loss to supervise the mutual learning of the NeRF style module and fine-tune the 2D stylization decoder. In order to further make our model handle ambiguities of 2D stylization results, we introduce learnable latent codes that obey the probability distributions conditioned on the style. They are attached to training samples as conditional inputs to better learn the style module in our novel stylized NeRF. Experimental results demonstrate that our method is superior to existing approaches in both visual quality and long-range consistency.

Lin Gao, Jia-Mu Sun, Kaichun Mo et al.

3D indoor scenes are widely used in computer graphics, with applications ranging from interior design to gaming to virtual and augmented reality. They also contain rich information, including room layout, as well as furniture type, geometry, and placement. High-quality 3D indoor scenes are highly demanded while it requires expertise and is time-consuming to design high-quality 3D indoor scenes manually. Existing research only addresses partial problems: some works learn to generate room layout, and other works focus on generating detailed structure and geometry of individual furniture objects. However, these partial steps are related and should be addressed together for optimal synthesis. We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level. Therefore for the first time, our method is able to directly generate plausible 3D room content, including furniture objects with fine-grained geometry, and their layout. To address the challenge, we introduce functional regions as intermediate proxies between the room and object levels to make learning more manageable. To ensure plausibility, our graph-based representation incorporates both vertical edges connecting child nodes with parent nodes from different levels, and horizontal edges encoding relationships between nodes at the same level. Extensive experiments demonstrate that our method produces superior generation results, even when comparing results of partial steps with alternative methods that can only achieve these. We also demonstrate that our method is effective for various applications such as part-level room editing, room interpolation, and room generation by arbitrary room boundaries.

Qiao Feng, Yebin Liu, Yu-Kun Lai et al.

The advent of deep learning has led to significant progress in monocular human reconstruction. However, existing representations, such as parametric models, voxel grids, meshes and implicit neural representations, have difficulties achieving high-quality results and real-time speed at the same time. In this paper, we propose Fourier Occupancy Field (FOF), a novel powerful, efficient and flexible 3D representation, for monocular real-time and accurate human reconstruction. The FOF represents a 3D object with a 2D field orthogonal to the view direction where at each 2D position the occupancy field of the object along the view direction is compactly represented with the first few terms of Fourier series, which retains the topology and neighborhood relation in the 2D domain. A FOF can be stored as a multi-channel image, which is compatible with 2D convolutional neural networks and can bridge the gap between 3D geometries and 2D images. The FOF is very flexible and extensible, e.g., parametric models can be easily integrated into a FOF as a prior to generate more robust results. Based on FOF, we design the first 30+FPS high-fidelity real-time monocular human reconstruction framework. We demonstrate the potential of FOF on both public dataset and real captured data. The code will be released for research purposes.

Chuanyu Pan, Guowei Yang, Taijiang Mu et al.

With the booming of virtual reality (VR) technology, there is a growing need for customized 3D avatars. However, traditional methods for 3D avatar modeling are either time-consuming or fail to retain similarity to the person being modeled. We present a novel framework to generate animatable 3D cartoon faces from a single portrait image. We first transfer an input real-world portrait to a stylized cartoon image with a StyleGAN. Then we propose a two-stage reconstruction method to recover the 3D cartoon face with detailed texture, which first makes a coarse estimation based on template models, and then refines the model by non-rigid deformation under landmark supervision. Finally, we propose a semantic preserving face rigging method based on manually created templates and deformation transfer. Compared with prior arts, qualitative and quantitative results show that our method achieves better accuracy, aesthetics, and similarity criteria. Furthermore, we demonstrate the capability of real-time facial animation of our 3D model.

Haotian Yang, Mingwu Zheng, Wanquan Feng et al.

In this paper, we propose a novel framework, Tracking-free Relightable Avatar (TRAvatar), for capturing and reconstructing high-fidelity 3D avatars. Compared to previous methods, TRAvatar works in a more practical and efficient setting. Specifically, TRAvatar is trained with dynamic image sequences captured in a Light Stage under varying lighting conditions, enabling realistic relighting and real-time animation for avatars in diverse scenes. Additionally, TRAvatar allows for tracking-free avatar capture and obviates the need for accurate surface tracking under varying illumination conditions. Our contributions are two-fold: First, we propose a novel network architecture that explicitly builds on and ensures the satisfaction of the linear nature of lighting. Trained on simple group light captures, TRAvatar can predict the appearance in real-time with a single forward pass, achieving high-quality relighting effects under illuminations of arbitrary environment maps. Second, we jointly optimize the facial geometry and relightable appearance from scratch based on image sequences, where the tracking is implicitly learned. This tracking-free approach brings robustness for establishing temporal correspondences between frames under different lighting conditions. Extensive qualitative and quantitative experiments demonstrate that our framework achieves superior performance for photorealistic avatar animation and relighting.

Shuang Song, Yuanbang Liang, Jing Wu et al.

Despite the success of StyleGAN in image synthesis, the images it synthesizes are not always perfect and the well-known truncation trick has become a standard post-processing technique for StyleGAN to synthesize high-quality images. Although effective, it has long been noted that the truncation trick tends to reduce the diversity of synthesized images and unnecessarily sacrifices many distinct image features. To address this issue, in this paper, we first delve into the StyleGAN image synthesis mechanism and discover an important phenomenon, namely Feature Proliferation, which demonstrates how specific features reproduce with forward propagation. Then, we show how the occurrence of Feature Proliferation results in StyleGAN image artifacts. As an analogy, we refer to it as the" cancer" in StyleGAN from its proliferating and malignant nature. Finally, we propose a novel feature rescaling method that identifies and modulates risky features to mitigate feature proliferation. Thanks to our discovery of Feature Proliferation, the proposed feature rescaling method is less destructive and retains more useful image features than the truncation trick, as it is more fine-grained and works in a lower-level feature space rather than a high-level latent space. Experimental results justify the validity of our claims and the effectiveness of the proposed feature rescaling method. Our code is available at https://github. com/songc42/Feature-proliferation.

Meihao Kong, Jing Huo, Wenbin Li et al.

Style transfer has achieved great success and attracted a wide range of attention from both academic and industrial communities due to its flexible application scenarios. However, the dependence on a pretty large VGG-based autoencoder leads to existing style transfer models having high parameter complexities, which limits their applications on resource-constrained devices. Compared with many other tasks, the compression of style transfer models has been less explored. Recently, the lottery ticket hypothesis (LTH) has shown great potential in finding extremely sparse matching subnetworks which can achieve on par or even better performance than the original full networks when trained in isolation. In this work, we for the first time perform an empirical study to verify whether such trainable matching subnetworks also exist in style transfer models. Specifically, we take two most popular style transfer models, i.e., AdaIN and SANet, as the main testbeds, which represent global and local transformation based style transfer methods respectively. We carry out extensive experiments and comprehensive analysis, and draw the following conclusions. (1) Compared with fixing the VGG encoder, style transfer models can benefit more from training the whole network together. (2) Using iterative magnitude pruning, we find the matching subnetworks at 89.2% sparsity in AdaIN and 73.7% sparsity in SANet, which demonstrates that style transfer models can play lottery tickets too. (3) The feature transformation module should also be pruned to obtain a much sparser model without affecting the existence and quality of the matching subnetworks. (4) Besides AdaIN and SANet, other models such as LST, MANet, AdaAttN and MCCNet can also play lottery tickets, which shows that LTH can be generalized to various style transfer models.

Tian-Xing Xu, Yuan-Chen Guo, Yu-Kun Lai et al.

3D single object tracking plays an essential role in many applications, such as autonomous driving. It remains a challenging problem due to the large appearance variation and the sparsity of points caused by occlusion and limited sensor capabilities. Therefore, contextual information across two consecutive frames is crucial for effective object tracking. However, points containing such useful information are often overlooked and cropped out in existing methods, leading to insufficient use of important contextual knowledge. To address this issue, we propose CXTrack, a novel transformer-based network for 3D object tracking, which exploits ConteXtual information to improve the tracking results. Specifically, we design a target-centric transformer network that directly takes point features from two consecutive frames and the previous bounding box as input to explore contextual information and implicitly propagate target cues. To achieve accurate localization for objects of all sizes, we propose a transformer-based localization head with a novel center embedding module to distinguish the target from distractors. Extensive experiments on three large-scale datasets, KITTI, nuScenes and Waymo Open Dataset, show that CXTrack achieves state-of-the-art tracking performance while running at 34 FPS.

Bo Li, Kaitao Xue, Bin Liu et al.

Image-to-image translation is an important and challenging problem in computer vision and image processing. Diffusion models (DM) have shown great potentials for high-quality image synthesis, and have gained competitive performance on the task of image-to-image translation. However, most of the existing diffusion models treat image-to-image translation as conditional generation processes, and suffer heavily from the gap between distinct domains. In this paper, a novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM) is proposed, which models image-to-image translation as a stochastic Brownian bridge process, and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process. To the best of our knowledge, it is the first work that proposes Brownian Bridge diffusion process for image-to-image translation. Experimental results on various benchmarks demonstrate that the proposed BBDM model achieves competitive performance through both visual inspection and measurable metrics.

Xintong Yang, Ze Ji, Jing Wu et al.

As a popular concept proposed in the field of psychology, affordance has been regarded as one of the important abilities that enable humans to understand and interact with the environment. Briefly, it captures the possibilities and effects of the actions of an agent applied to a specific object or, more generally, a part of the environment. This paper provides a short review of the recent developments of deep robotic affordance learning (DRAL), which aims to develop data-driven methods that use the concept of affordance to aid in robotic tasks. We first classify these papers from a reinforcement learning (RL) perspective, and draw connections between RL and affordances. The technical details of each category are discussed and their limitations identified. We further summarise them and identify future challenges from the aspects of observations, actions, affordance representation, data-collection and real-world deployment. A final remark is given at the end to propose a promising future direction of the RL-based affordance definition to include the predictions of arbitrary action consequences.

Tian-Xing Xu, Yuan-Chen Guo, Yu-Kun Lai et al.

3D single object tracking has been a crucial problem for decades with numerous applications such as autonomous driving. Despite its wide-ranging use, this task remains challenging due to the significant appearance variation caused by occlusion and size differences among tracked targets. To address these issues, we present MBPTrack, which adopts a Memory mechanism to utilize past information and formulates localization in a coarse-to-fine scheme using Box Priors given in the first frame. Specifically, past frames with targetness masks serve as an external memory, and a transformer-based module propagates tracked target cues from the memory to the current frame. To precisely localize objects of all sizes, MBPTrack first predicts the target center via Hough voting. By leveraging box priors given in the first frame, we adaptively sample reference points around the target center that roughly cover the target of different sizes. Then, we obtain dense feature maps by aggregating point features into the reference points, where localization can be performed more effectively. Extensive experiments demonstrate that MBPTrack achieves state-of-the-art performance on KITTI, nuScenes and Waymo Open Dataset, while running at 50 FPS on a single RTX3090 GPU.

Yi Wang, Jian Ma, Ruizhi Shao et al.

This paper aims to generate physically-layered 3D humans from text prompts. Existing methods either generate 3D clothed humans as a whole or support only tight and simple clothing generation, which limits their applications to virtual try-on and part-level editing. To achieve physically-layered 3D human generation with reusable and complex clothing, we propose a novel layer-wise dressed human representation based on a physically-decoupled diffusion model. Specifically, to achieve layer-wise clothing generation, we propose a dual-representation decoupling framework for generating clothing decoupled from the human body, in conjunction with an innovative multi-layer fusion volume rendering method. To match the clothing with different body shapes, we propose an SMPL-driven implicit field deformation network that enables the free transfer and reuse of clothing. Extensive experiments demonstrate that our approach not only achieves state-of-the-art layered 3D human generation with complex clothing but also supports virtual try-on and layered human animation.

Xintong Yang, Ze Ji, Jing Wu et al.

Although Deep Reinforcement Learning (DRL) has been popular in many disciplines including robotics, state-of-the-art DRL algorithms still struggle to learn long-horizon, multi-step and sparse reward tasks, such as stacking several blocks given only a task-completion reward signal. To improve learning efficiency for such tasks, this paper proposes a DRL exploration technique, termed A^2, which integrates two components inspired by human experiences: Abstract demonstrations and Adaptive exploration. A^2 starts by decomposing a complex task into subtasks, and then provides the correct orders of subtasks to learn. During training, the agent explores the environment adaptively, acting more deterministically for well-mastered subtasks and more stochastically for ill-learnt subtasks. Ablation and comparative experiments are conducted on several grid-world tasks and three robotic manipulation tasks. We demonstrate that A^2 can aid popular DRL algorithms (DQN, DDPG, and SAC) to learn more efficiently and stably in these environments.

Yuanbang Liang, Jing Wu, Yu-Kun Lai et al.

Despite the extensive studies on Generative Adversarial Networks (GANs), how to reliably sample high-quality images from their latent spaces remains an under-explored topic. In this paper, we propose a novel GAN latent sampling method by exploring and exploiting the hubness priors of GAN latent distributions. Our key insight is that the high dimensionality of the GAN latent space will inevitably lead to the emergence of hub latents that usually have much larger sampling densities than other latents in the latent space. As a result, these hub latents are better trained and thus contribute more to the synthesis of high-quality images. Unlike the a posterior "cherry-picking", our method is highly efficient as it is an a priori method that identifies high-quality latents before the synthesis of images. Furthermore, we show that the well-known but purely empirical truncation trick is a naive approximation to the central clustering effect of hub latents, which not only uncovers the rationale of the truncation trick, but also indicates the superiority and fundamentality of our method. Extensive experimental results demonstrate the effectiveness of the proposed method.

Yu-Jie Yuan, Leif Kobbelt, Jiwen Liu et al.

Due to the fascinating generative performance of text-to-image diffusion models, growing text-to-3D generation works explore distilling the 2D generative priors into 3D, using the score distillation sampling (SDS) loss, to bypass the data scarcity problem. The existing text-to-3D methods have achieved promising results in realism and 3D consistency, but text-to-4D generation still faces challenges, including lack of realism and insufficient dynamic motions. In this paper, we propose a novel method for text-to-4D generation, which ensures the dynamic amplitude and authenticity through direct supervision provided by a video prior. Specifically, we adopt a text-to-video diffusion model to generate a reference video and divide 4D generation into two stages: static generation and dynamic generation. The static 3D generation is achieved under the guidance of the input text and the first frame of the reference video, while in the dynamic generation stage, we introduce a customized SDS loss to ensure multi-view consistency, a video-based SDS loss to improve temporal consistency, and most importantly, direct priors from the reference video to ensure the quality of geometry and texture. Moreover, we design a prior-switching training strategy to avoid conflicts between different priors and fully leverage the benefits of each prior. In addition, to enrich the generated motion, we further introduce a dynamic modeling representation composed of a deformation network and a topology network, which ensures dynamic continuity while modeling topological changes. Our method not only supports text-to-4D generation but also enables 4D generation from monocular videos. The comparison experiments demonstrate the superiority of our method compared to existing methods.

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.

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.

Haokun Zhu, Juang Ian Chong, Teng Hu et al.

Vector graphics are widely used in graphical designs and have received more and more attention. However, unlike raster images which can be easily obtained, acquiring high-quality vector graphics, typically through automatically converting from raster images remains a significant challenge, especially for more complex images such as photos or artworks. In this paper, we propose SAMVG, a multi-stage model to vectorize raster images into SVG (Scalable Vector Graphics). Firstly, SAMVG uses general image segmentation provided by the Segment-Anything Model and uses a novel filtering method to identify the best dense segmentation map for the entire image. Secondly, SAMVG then identifies missing components and adds more detailed components to the SVG. Through a series of extensive experiments, we demonstrate that SAMVG can produce high quality SVGs in any domain while requiring less computation time and complexity compared to previous state-of-the-art methods.

Bin Liu, Xiaolin Wei, Bo Li et al.

Most of the existing audio-driven 3D facial animation methods suffered from the lack of detailed facial expression and head pose, resulting in unsatisfactory experience of human-robot interaction. In this paper, a novel pose-controllable 3D facial animation synthesis method is proposed by utilizing hierarchical audio-vertex attention. To synthesize real and detailed expression, a hierarchical decomposition strategy is proposed to encode the audio signal into both a global latent feature and a local vertex-wise control feature. Then the local and global audio features combined with vertex spatial features are used to predict the final consistent facial animation via a graph convolutional neural network by fusing the intrinsic spatial topology structure of the face model and the corresponding semantic feature of the audio. To accomplish pose-controllable animation, we introduce a novel pose attribute augmentation method by utilizing the 2D talking face technique. Experimental results indicate that the proposed method can produce more realistic facial expressions and head posture movements. Qualitative and quantitative experiments show that the proposed method achieves competitive performance against state-of-the-art methods.

Xintong Yang, Ze Ji, Yu-Kun Lai

Robotic manipulation of volumetric elastoplastic deformable materials, from foods such as dough to construction materials like clay, is in its infancy, largely due to the difficulty of modelling and perception in a high-dimensional space. Simulating the dynamics of such materials is computationally expensive. It tends to suffer from inaccurately estimated physics parameters of the materials and the environment, impeding high-precision manipulation. Estimating such parameters from raw point clouds captured by optical cameras suffers further from heavy occlusions. To address this challenge, this work introduces a novel Differentiable Physics-based System Identification (DPSI) framework that enables a robot arm to infer the physics parameters of elastoplastic materials and the environment using simple manipulation motions and incomplete 3D point clouds, aligning the simulation with the real world. Extensive experiments show that with only a single real-world interaction, the estimated parameters, Young's modulus, Poisson's ratio, yield stress and friction coefficients, can accurately simulate visually and physically realistic deformation behaviours induced by unseen and long-horizon manipulation motions. Additionally, the DPSI framework inherently provides physically intuitive interpretations for the parameters in contrast to black-box approaches such as deep neural networks. The project is fully open-sourced via https://ianyangchina.github.io/SI4RP-data/.

Yixiao Li, Xiaoyuan Yang, Weide Liu et al.

As super-resolution (SR) techniques introduce unique distortions that fundamentally differ from those caused by traditional degradation processes (e.g., compression), there is an increasing demand for specialized video quality assessment (VQA) methods tailored to SR-generated content. One critical factor affecting perceived quality is temporal inconsistency, which refers to irregularities between consecutive frames. However, existing VQA approaches rarely quantify this phenomenon or explicitly investigate its relationship with human perception. Moreover, SR videos exhibit amplified inconsistency levels as a result of enhancement processes. In this paper, we propose \textit{Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment (TIG-SVQA)} that underscores the critical role of temporal inconsistency in guiding the quality assessment of SR videos. We first design a perception-oriented approach to quantify frame-wise temporal inconsistency. Based on this, we introduce the Inconsistency Highlighted Spatial Module, which localizes inconsistent regions at both coarse and fine scales. Inspired by the human visual system, we further develop an Inconsistency Guided Temporal Module that performs progressive temporal feature aggregation: (1) a consistency-aware fusion stage in which a visual memory capacity block adaptively determines the information load of each temporal segment based on inconsistency levels, and (2) an informative filtering stage for emphasizing quality-related features. Extensive experiments on both single-frame and multi-frame SR video scenarios demonstrate that our method significantly outperforms state-of-the-art VQA approaches. The code is publicly available at https://github.com/Lighting-YXLI/TIG-SVQA-main.

Mingchen Xu, Jing Wu, Yukun Lai et al.

Techniques for detecting mirrors from static images have witnessed rapid growth in recent years. However, these methods detect mirrors from single input images. Detecting mirrors from video requires further consideration of temporal consistency between frames. We observe that humans can recognize mirror candidates, from just one or two frames, based on their appearance (e.g. shape, color). However, to ensure that the candidate is indeed a mirror (not a picture or a window), we often need to observe more frames for a global view. This observation motivates us to detect mirrors by fusing appearance features extracted from a short-term attention module and context information extracted from a long-term attention module. To evaluate the performance, we build a challenging benchmark dataset of 19,255 frames from 281 videos. Experimental results demonstrate that our method achieves state-of-the-art performance on the benchmark dataset.

Qingmeng Wen, Yu-Kun Lai, Ze Ji et al.

Skeletonization is a powerful tool for shape analysis, rooted in the inherent instinct to understand an object's morphology. It has found applications across various domains, including robotics. Although skeletonization algorithms have been studied in recent years, their performance is rarely quantified with detailed numerical evaluations. This work focuses on defining and quantifying geometric properties to systematically score the skeletonization results of point cloud shapes across multiple aspects, including topological similarity, boundedness, centeredness, and smoothness. We introduce these representative metric definitions along with a numerical scoring framework to analyze skeletonization outcomes concerning point cloud data for different scenarios, from object manipulation to mobile robot navigation. Additionally, we provide an open-source tool to enable the research community to evaluate and refine their skeleton models. Finally, we assess the performance and sensitivity of the proposed geometric evaluation methods from various robotic applications.

Teng Hu, Ran Yi, Baihong Qian et al.

SVG (Scalable Vector Graphics) is a widely used graphics format that possesses excellent scalability and editability. Image vectorization, which aims to convert raster images to SVGs, is an important yet challenging problem in computer vision and graphics. Existing image vectorization methods either suffer from low reconstruction accuracy for complex images or require long computation time. To address this issue, we propose SuperSVG, a superpixel-based vectorization model that achieves fast and high-precision image vectorization. Specifically, we decompose the input image into superpixels to help the model focus on areas with similar colors and textures. Then, we propose a two-stage self-training framework, where a coarse-stage model is employed to reconstruct the main structure and a refinement-stage model is used for enriching the details. Moreover, we propose a novel dynamic path warping loss to help the refinement-stage model to inherit knowledge from the coarse-stage model. Extensive qualitative and quantitative experiments demonstrate the superior performance of our method in terms of reconstruction accuracy and inference time compared to state-of-the-art approaches. The code is available in \url{https://github.com/sjtuplayer/SuperSVG}.

Xintong Yang, Ze Ji, Jing Wu et al.

This work re-implements the OpenAI Gym multi-goal robotic manipulation environment, originally based on the commercial Mujoco engine, onto the open-source Pybullet engine. By comparing the performances of the Hindsight Experience Replay-aided Deep Deterministic Policy Gradient agent on both environments, we demonstrate our successful re-implementation of the original environment. Besides, we provide users with new APIs to access a joint control mode, image observations and goals with customisable camera and a built-in on-hand camera. We further design a set of multi-step, multi-goal, long-horizon and sparse reward robotic manipulation tasks, aiming to inspire new goal-conditioned reinforcement learning algorithms for such challenges. We use a simple, human-prior-based curriculum learning method to benchmark the multi-step manipulation tasks. Discussions about future research opportunities regarding this kind of tasks are also provided.

Rao Fu, Jie Yang, Jiawei Sun et al.

Fine-grained 3D shape retrieval aims to retrieve 3D shapes similar to a query shape in a repository with models belonging to the same class, which requires shape descriptors to be capable of representing detailed geometric information to discriminate shapes with globally similar structures. Moreover, 3D objects can be placed with arbitrary position and orientation in real-world applications, which further requires shape descriptors to be robust to rigid transformations. The shape descriptions used in existing 3D shape retrieval systems fail to meet the above two criteria. In this paper, we introduce a novel deep architecture, RISA-Net, which learns rotation invariant 3D shape descriptors that are capable of encoding fine-grained geometric information and structural information, and thus achieve accurate results on the task of fine-grained 3D object retrieval. RISA-Net extracts a set of compact and detailed geometric features part-wisely and discriminatively estimates the contribution of each semantic part to shape representation. Furthermore, our method is able to learn the importance of geometric and structural information of all the parts when generating the final compact latent feature of a 3D shape for fine-grained retrieval. We also build and publish a new 3D shape dataset with sub-class labels for validating the performance of fine-grained 3D shape retrieval methods. Qualitative and quantitative experiments show that our RISA-Net outperforms state-of-the-art methods on the fine-grained object retrieval task, demonstrating its capability in geometric detail extraction. The code and dataset are available at: https://github.com/IGLICT/RisaNET.

Jie Yang, Kaichun Mo, Yu-Kun Lai et al.

D shape generation is a fundamental operation in computer graphics. While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric details and complex structure, in a controllable manner. To tackle this, we introduce DSG-Net, a deep neural network that learns a disentangled structured and geometric mesh representation for 3D shapes, where two key aspects of shapes, geometry, and structure, are encoded in a synergistic manner to ensure plausibility of the generated shapes, while also being disentangled as much as possible. This supports a range of novel shape generation applications with disentangled control, such as interpolation of structure (geometry) while keeping geometry (structure) unchanged. To achieve this, we simultaneously learn structure and geometry through variational autoencoders (VAEs) in a hierarchical manner for both, with bijective mappings at each level. In this manner, we effectively encode geometry and structure in separate latent spaces, while ensuring their compatibility: the structure is used to guide the geometry and vice versa. At the leaf level, the part geometry is represented using a conditional part VAE, to encode high-quality geometric details, guided by the structure context as the condition. Our method not only supports controllable generation applications but also produces high-quality synthesized shapes, outperforming state-of-the-art methods. The code has been released at https://github.com/IGLICT/DSG-Net.

Jing Huo, Shiyin Jin, Wenbin Li et al.

Most existing style transfer methods follow the assumption that styles can be represented with global statistics (e.g., Gram matrices or covariance matrices), and thus address the problem by forcing the output and style images to have similar global statistics. An alternative is the assumption of local style patterns, where algorithms are designed to swap similar local features of content and style images. However, the limitation of these existing methods is that they neglect the semantic structure of the content image which may lead to corrupted content structure in the output. In this paper, we make a new assumption that image features from the same semantic region form a manifold and an image with multiple semantic regions follows a multi-manifold distribution. Based on this assumption, the style transfer problem is formulated as aligning two multi-manifold distributions and a Manifold Alignment based Style Transfer (MAST) framework is proposed. The proposed framework allows semantically similar regions between the output and the style image share similar style patterns. Moreover, the proposed manifold alignment method is flexible to allow user editing or using semantic segmentation maps as guidance for style transfer. To allow the method to be applicable to photorealistic style transfer, we propose a new adaptive weight skip connection network structure to preserve the content details. Extensive experiments verify the effectiveness of the proposed framework for both artistic and photorealistic style transfer. Code is available at https://github.com/NJUHuoJing/MAST.

Qian Xie, Yu-Kun Lai, Jing Wu et al.

In this paper, we address the 3D object detection task by capturing multi-level contextual information with the self-attention mechanism and multi-scale feature fusion. Most existing 3D object detection methods recognize objects individually, without giving any consideration on contextual information between these objects. Comparatively, we propose Multi-Level Context VoteNet (MLCVNet) to recognize 3D objects correlatively, building on the state-of-the-art VoteNet. We introduce three context modules into the voting and classifying stages of VoteNet to encode contextual information at different levels. Specifically, a Patch-to-Patch Context (PPC) module is employed to capture contextual information between the point patches, before voting for their corresponding object centroid points. Subsequently, an Object-to-Object Context (OOC) module is incorporated before the proposal and classification stage, to capture the contextual information between object candidates. Finally, a Global Scene Context (GSC) module is designed to learn the global scene context. We demonstrate these by capturing contextual information at patch, object and scene levels. Our method is an effective way to promote detection accuracy, achieving new state-of-the-art detection performance on challenging 3D object detection datasets, i.e., SUN RGBD and ScanNet. We also release our code at https://github.com/NUAAXQ/MLCVNet.

Lin Gao, Jie Yang, Bo-Tao Zhang et al.

Neural implicit representations, including Neural Distance Fields and Neural Radiance Fields, have demonstrated significant capabilities for reconstructing surfaces with complicated geometry and topology, and generating novel views of a scene. Nevertheless, it is challenging for users to directly deform or manipulate these implicit representations with large deformations in the real-time fashion. Gaussian Splatting(GS) has recently become a promising method with explicit geometry for representing static scenes and facilitating high-quality and real-time synthesis of novel views. However,it cannot be easily deformed due to the use of discrete Gaussians and lack of explicit topology. To address this, we develop a novel GS-based method that enables interactive deformation. Our key idea is to design an innovative mesh-based GS representation, which is integrated into Gaussian learning and manipulation. 3D Gaussians are defined over an explicit mesh, and they are bound with each other: the rendering of 3D Gaussians guides the mesh face split for adaptive refinement, and the mesh face split directs the splitting of 3D Gaussians. Moreover, the explicit mesh constraints help regularize the Gaussian distribution, suppressing poor-quality Gaussians(e.g. misaligned Gaussians,long-narrow shaped Gaussians), thus enhancing visual quality and avoiding artifacts during deformation. Based on this representation, we further introduce a large-scale Gaussian deformation technique to enable deformable GS, which alters the parameters of 3D Gaussians according to the manipulation of the associated mesh. Our method benefits from existing mesh deformation datasets for more realistic data-driven Gaussian deformation. Extensive experiments show that our approach achieves high-quality reconstruction and effective deformation, while maintaining the promising rendering results at a high frame rate(65 FPS on average).

Tong Wu, Jia-Mu Sun, Yu-Kun Lai et al.

Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstruction and editing results but suffer from inefficiency in rendering. Gaussian splatting significantly accelerates rendering by rasterizing Gaussian ellipsoids. However, Gaussian splatting utilizes a single Spherical Harmonic (SH) function to model both texture and lighting, limiting independent editing capabilities of these components. Recently, attempts have been made to decouple texture and lighting with the Gaussian splatting representation but may fail to produce plausible geometry and decomposition results on reflective scenes. Additionally, the forward shading technique they employ introduces noticeable blending artifacts during relighting, as the geometry attributes of Gaussians are optimized under the original illumination and may not be suitable for novel lighting conditions. To address these issues, we introduce DeferredGS, a method for decoupling and editing the Gaussian splatting representation using deferred shading. To achieve successful decoupling, we model the illumination with a learnable environment map and define additional attributes such as texture parameters and normal direction on Gaussians, where the normal is distilled from a jointly trained signed distance function. More importantly, we apply deferred shading, resulting in more realistic relighting effects compared to previous methods. Both qualitative and quantitative experiments demonstrate the superior performance of DeferredGS in novel view synthesis and editing tasks.

Tian-Xing Xu, Wenbo Hu, Yu-Kun Lai et al.

3D Gaussian splatting, emerging as a groundbreaking approach, has drawn increasing attention for its capabilities of high-fidelity reconstruction and real-time rendering. However, it couples the appearance and geometry of the scene within the Gaussian attributes, which hinders the flexibility of editing operations, such as texture swapping. To address this issue, we propose a novel approach, namely Texture-GS, to disentangle the appearance from the geometry by representing it as a 2D texture mapped onto the 3D surface, thereby facilitating appearance editing. Technically, the disentanglement is achieved by our proposed texture mapping module, which consists of a UV mapping MLP to learn the UV coordinates for the 3D Gaussian centers, a local Taylor expansion of the MLP to efficiently approximate the UV coordinates for the ray-Gaussian intersections, and a learnable texture to capture the fine-grained appearance. Extensive experiments on the DTU dataset demonstrate that our method not only facilitates high-fidelity appearance editing but also achieves real-time rendering on consumer-level devices, e.g. a single RTX 2080 Ti GPU.

Ziqi Cai, Kaiwen Jiang, Shu-Yu Chen et al.

Synthesizing realistic videos of talking faces under custom lighting conditions and viewing angles benefits various downstream applications like video conferencing. However, most existing relighting methods are either time-consuming or unable to adjust the viewpoints. In this paper, we present the first real-time 3D-aware method for relighting in-the-wild videos of talking faces based on Neural Radiance Fields (NeRF). Given an input portrait video, our method can synthesize talking faces under both novel views and novel lighting conditions with a photo-realistic and disentangled 3D representation. Specifically, we infer an albedo tri-plane, as well as a shading tri-plane based on a desired lighting condition for each video frame with fast dual-encoders. We also leverage a temporal consistency network to ensure smooth transitions and reduce flickering artifacts. Our method runs at 32.98 fps on consumer-level hardware and achieves state-of-the-art results in terms of reconstruction quality, lighting error, lighting instability, temporal consistency and inference speed. We demonstrate the effectiveness and interactivity of our method on various portrait videos with diverse lighting and viewing conditions.

Haotian Yang, Mingwu Zheng, Chongyang Ma et al.

In this paper, we introduce the Volumetric Relightable Morphable Model (VRMM), a novel volumetric and parametric facial prior for 3D face modeling. While recent volumetric prior models offer improvements over traditional methods like 3D Morphable Models (3DMMs), they face challenges in model learning and personalized reconstructions. Our VRMM overcomes these by employing a novel training framework that efficiently disentangles and encodes latent spaces of identity, expression, and lighting into low-dimensional representations. This framework, designed with self-supervised learning, significantly reduces the constraints for training data, making it more feasible in practice. The learned VRMM offers relighting capabilities and encompasses a comprehensive range of expressions. We demonstrate the versatility and effectiveness of VRMM through various applications like avatar generation, facial reconstruction, and animation. Additionally, we address the common issue of overfitting in generative volumetric models with a novel prior-preserving personalization framework based on VRMM. Such an approach enables high-quality 3D face reconstruction from even a single portrait input. Our experiments showcase the potential of VRMM to significantly enhance the field of 3D face modeling.

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.

Yi-Hua Huang, Yan-Pei Cao, Yu-Kun Lai et al.

Texture synthesis is a fundamental problem in computer graphics that would benefit various applications. Existing methods are effective in handling 2D image textures. In contrast, many real-world textures contain meso-structure in the 3D geometry space, such as grass, leaves, and fabrics, which cannot be effectively modeled using only 2D image textures. We propose a novel texture synthesis method with Neural Radiance Fields (NeRF) to capture and synthesize textures from given multi-view images. In the proposed NeRF texture representation, a scene with fine geometric details is disentangled into the meso-structure textures and the underlying base shape. This allows textures with meso-structure to be effectively learned as latent features situated on the base shape, which are fed into a NeRF decoder trained simultaneously to represent the rich view-dependent appearance. Using this implicit representation, we can synthesize NeRF-based textures through patch matching of latent features. However, inconsistencies between the metrics of the reconstructed content space and the latent feature space may compromise the synthesis quality. To enhance matching performance, we further regularize the distribution of latent features by incorporating a clustering constraint. In addition to generating NeRF textures over a planar domain, our method can also synthesize NeRF textures over curved surfaces, which are practically useful. Experimental results and evaluations demonstrate the effectiveness of our approach.

Mingchen Xu, Yukun Lai, Ze Ji et al.

This paper presents MirrorSAM2, the first framework that adapts Segment Anything Model 2 (SAM2) to the task of RGB-D video mirror segmentation. MirrorSAM2 addresses key challenges in mirror detection, such as reflection ambiguity and texture confusion, by introducing four tailored modules: a Depth Warping Module for RGB and depth alignment, a Depth-guided Multi-Scale Point Prompt Generator for automatic prompt generation, a Frequency Detail Attention Fusion Module to enhance structural boundaries, and a Mirror Mask Decoder with a learnable mirror token for refined segmentation. By fully leveraging the complementarity between RGB and depth, MirrorSAM2 extends SAM2's capabilities to the prompt-free setting. To our knowledge, this is the first work to enable SAM2 for automatic video mirror segmentation. Experiments on the VMD and DVMD benchmark demonstrate that MirrorSAM2 achieves SOTA performance, even under challenging conditions such as small mirrors, weak boundaries, and strong reflections.

Yizhe Tang, Yue Wang, Teng Hu et al.

Stroke-based Rendering (SBR) aims to decompose an input image into a sequence of parameterized strokes, which can be rendered into a painting that resembles the input image. Recently, Neural Painting methods that utilize deep learning and reinforcement learning models to predict the stroke sequences have been developed, but suffer from longer inference time or unstable training. To address these issues, we propose AttentionPainter, an efficient and adaptive model for single-step neural painting. First, we propose a novel scalable stroke predictor, which predicts a large number of stroke parameters within a single forward process, instead of the iterative prediction of previous Reinforcement Learning or auto-regressive methods, which makes AttentionPainter faster than previous neural painting methods. To further increase the training efficiency, we propose a Fast Stroke Stacking algorithm, which brings 13 times acceleration for training. Moreover, we propose Stroke-density Loss, which encourages the model to use small strokes for detailed information, to help improve the reconstruction quality. Finally, we propose a new stroke diffusion model for both conditional and unconditional stroke-based generation, which denoises in the stroke parameter space and facilitates stroke-based inpainting and editing applications helpful for human artists design. Extensive experiments show that AttentionPainter outperforms the state-of-the-art neural painting methods.

Lianghan Zhu, Yanqi Bao, Jing Huo et al.

The rapid advancement in visual generation, particularly the emergence of pre-trained text-to-image and text-to-video models, has catalyzed growing interest in training-free video editing research. Mirroring training-free image editing techniques, current approaches preserve original video information through video input inversion and manipulating intermediate features and attention during the inference process to achieve content editing. Although they have demonstrated promising results, the lossy nature of the inversion process poses significant challenges in maintaining unedited regions of the video. Furthermore, feature and attention manipulation during inference can lead to unintended over-editing and face challenges in both local temporal continuity and global content consistency. To address these challenges, this study proposes a score distillation paradigm based on pre-trained text-to-video models, where the original video is iteratively optimized through multiple steps guided by editing gradients provided by score distillation to ultimately obtain the target video. The iterative optimization starting from the original video, combined with content preservation loss, ensures the maintenance of unedited regions in the original video and suppresses over-editing. To further guarantee video content consistency and temporal continuity, we additionally introduce a global consistency auxiliary loss and optical flow prediction-based local editing gradient smoothing. Experiments demonstrate that these strategies effectively address the aforementioned challenges, achieving comparable or superior performance across multiple dimensions including preservation of unedited regions, local temporal continuity, and global content consistency of editing results, compared to state-of-the-art methods.

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.

Yi Wang, Jian Ma, Ruizhi Shao et al.

The generation of 3D clothed humans has attracted increasing attention in recent years. However, existing work cannot generate layered high-quality 3D humans with consistent body structures. As a result, these methods are unable to arbitrarily and separately change and edit the body and clothing of the human. In this paper, we propose a text-driven layered 3D human generation framework based on a novel physically-decoupled semantic-aware diffusion model. To keep the generated clothing consistent with the target text, we propose a semantic-confidence strategy for clothing that can eliminate the non-clothing content generated by the model. To match the clothing with different body shapes, we propose a SMPL-driven implicit field deformation network that enables the free transfer and reuse of clothing. Besides, we introduce uniform shape priors based on the SMPL model for body and clothing, respectively, which generates more diverse 3D content without being constrained by specific templates. The experimental results demonstrate that the proposed method not only generates 3D humans with consistent body structures but also allows free editing in a layered manner. The source code will be made public.

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.

Kunhao Yuan, Gerald Schaefer, Yu-Kun Lai et al.

Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotations required by supervised semantic segmentation (SSS) methods. Despite drastically reduced annotation costs, typical feature representations learned from WSSS are only representative of some salient parts of objects and less reliable compared to SSS due to the weak guidance during training. In this paper, we propose a novel Multi-Strategy Contrastive Learning (MuSCLe) framework to obtain enhanced feature representations and improve WSSS performance by exploiting similarity and dissimilarity of contrastive sample pairs at image, region, pixel and object boundary levels. Extensive experiments demonstrate the effectiveness of our method and show that MuSCLe outperforms the current state-of-the-art on the widely used PASCAL VOC 2012 dataset.

Zipeng Ye, Mengfei Xia, Ran Yi et al.

In this paper, we present a dynamic convolution kernel (DCK) strategy for convolutional neural networks. Using a fully convolutional network with the proposed DCKs, high-quality talking-face video can be generated from multi-modal sources (i.e., unmatched audio and video) in real time, and our trained model is robust to different identities, head postures, and input audios. Our proposed DCKs are specially designed for audio-driven talking face video generation, leading to a simple yet effective end-to-end system. We also provide a theoretical analysis to interpret why DCKs work. Experimental results show that our method can generate high-quality talking-face video with background at 60 fps. Comparison and evaluation between our method and the state-of-the-art methods demonstrate the superiority of our method.

Yang-tian Sun, Hao-zhi Huang, Xuan Wang et al.

Pose transfer of human videos aims to generate a high fidelity video of a target person imitating actions of a source person. A few studies have made great progress either through image translation with deep latent features or neural rendering with explicit 3D features. However, both of them rely on large amounts of training data to generate realistic results, and the performance degrades on more accessible internet videos due to insufficient training frames. In this paper, we demonstrate that the dynamic details can be preserved even trained from short monocular videos. Overall, we propose a neural video rendering framework coupled with an image-translation-based dynamic details generation network (D2G-Net), which fully utilizes both the stability of explicit 3D features and the capacity of learning components. To be specific, a novel texture representation is presented to encode both the static and pose-varying appearance characteristics, which is then mapped to the image space and rendered as a detail-rich frame in the neural rendering stage. Moreover, we introduce a concise temporal loss in the training stage to suppress the detail flickering that is made more visible due to high-quality dynamic details generated by our method. Through extensive comparisons, we demonstrate that our neural human video renderer is capable of achieving both clearer dynamic details and more robust performance even on accessible short videos with only 2k - 4k frames.

Tian-Xing Xu, Yuan-Chen Guo, Zhiqiang Li et al.

Place recognition plays an essential role in the field of autonomous driving and robot navigation. Point cloud based methods mainly focus on extracting global descriptors from local features of point clouds. Despite having achieved promising results, existing solutions neglect the following aspects, which may cause performance degradation: (1) huge size difference between objects in outdoor scenes; (2) moving objects that are unrelated to place recognition; (3) long-range contextual information. We illustrate that the above aspects bring challenges to extracting discriminative global descriptors. To mitigate these problems, we propose a novel method named TransLoc3D, utilizing adaptive receptive fields with a point-wise reweighting scheme to handle objects of different sizes while suppressing noises, and an external transformer to capture long-range feature dependencies. As opposed to existing architectures which adopt fixed and limited receptive fields, our method benefits from size-adaptive receptive fields as well as global contextual information, and outperforms current state-of-the-arts with significant improvements on popular datasets.

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.

Lan Chen, Lin Gao, Jie Yang et al.

In physics-based cloth animation, rich folds and detailed wrinkles are achieved at the cost of expensive computational resources and huge labor tuning. Data-driven techniques make efforts to reduce the computation significantly by a database. One type of methods relies on human poses to synthesize fitted garments which cannot be applied to general cloth. Another type of methods adds details to the coarse meshes without such restrictions. However, existing works usually utilize coordinate-based representations which cannot cope with large-scale deformation, and requires dense vertex correspondences between coarse and fine meshes. Moreover, as such methods only add details, they require coarse meshes to be close to fine meshes, which can be either impossible, or require unrealistic constraints when generating fine meshes. To address these challenges, we develop a temporally and spatially as-consistent-as-possible deformation representation (named TS-ACAP) and a DeformTransformer network to learn the mapping from low-resolution meshes to detailed ones. This TS-ACAP representation is designed to ensure both spatial and temporal consistency for sequential large-scale deformations from cloth animations. With this representation, our DeformTransformer network first utilizes two mesh-based encoders to extract the coarse and fine features, respectively. To transduct the coarse features to the fine ones, we leverage the Transformer network that consists of frame-level attention mechanisms to ensure temporal coherence of the prediction. Experimental results show that our method is able to produce reliable and realistic animations in various datasets at high frame rates: 10 ~ 35 times faster than physics-based simulation, with superior detail synthesis abilities than existing methods.