Publications

2025

1. TOG

   

   Patch-Grid: An Efficient and Feature-Preserving Neural Implicit Surface Representation

   Guying Lin^*, Lei Yang^*, Congyi Zhang , Hao Pan, Yuhan Ping , Guodong Wei, Taku Komura, John Keyser, and Wenping Wang

   ACM Trans. Graph., 2025

   (will be presented at SIGGRAPH 2025, * equal contribution)

   Abs arXiv

   

   Neural implicit representations are known to be more compact for depicting 3D shapes than traditional discrete representations. However, the neural representations tend to round sharp corners or edges and struggle to represent surfaces with open boundaries. Moreover, they are slow to train. We present a unified neural implicit representation, called Patch-Grid, that fits to complex shapes efficiently, preserves sharp features, and effectively models surfaces with open boundaries and thin geometric features. Our superior efficiency comes from embedding each surface patch into a local latent volume and decoding it using a shared MLP decoder, which is pretrained on various local surface geometries. With this pretrained decoder fixed, fitting novel shapes and local shape updates can be done efficiently. The faithful preservation of sharp features is enabled by adopting a novel merge grid to perform local constructive solid geometry (CSG) combinations of surface patches in the cells of an adaptive Octree, yielding better robustness than using a global CSG construction as proposed in the literature. Experiments show that our Patch-Grid method faithfully captures shapes with complex sharp features, open boundaries and thin structures, and outperforms existing learning-based methods in both efficiency and quality for surface fitting and local shape updates.

2024

1. SIGGRAPH 2024

   

   TexPainter: Generative Mesh Texturing with Multi-view Consistency

   Hongkun Zhang, Zherong Pan, Congyi Zhang, Lifeng Zhu, and Xifeng Gao

   In ACM SIGGRAPH 2024 Conference Papers, Denver, CO, USA, Jul 2024

   Abs DOI arXiv Code Website

   

   The recent success of pre-trained diffusion models unlocks the possibility of the automatic generation of textures for arbitrary 3D meshes in the wild. However, these models are trained in the screen space, while converting them to a multi-view consistent texture image poses a major obstacle to the output quality. In this paper, we propose a novel method to enforce multi-view consistency. Our method is based on the observation that latent space in a pre-trained diffusion model is noised separately for each camera view, making it difficult to achieve multi-view consistency by directly manipulating the latent codes. Based on the celebrated Denoising Diffusion Implicit Models (DDIM) scheme, we propose to use an optimization-based color-fusion to enforce consistency and indirectly modify the latent codes by gradient back-propagation. Our method further relaxes the sequential dependency assumption among the camera views. By evaluating on a series of general 3D models, we find our simple approach improves consistency and overall quality of the generated textures as compared to competing state-of-the-arts. Our implementation is available at: https://github.com/Quantuman134/TexPainter

2. TVCG

   

   Skull-to-Face: Anatomy-Guided 3D Facial Reconstruction and Editing

   Yongqing Liang, Congyi Zhang, Junli Zhao, Wenping Wang, and Xin Li

   IEEE Transactions on Visualization and Computer Graphics, Nov 2024

   Abs arXiv Code Website

   

   Deducing the 3D face from a skull is a challenging task in forensic science and archaeology. This paper proposes an end-to-end 3D face reconstruction pipeline and an exploration method that can conveniently create textured, realistic faces that match the given skull. To this end, we propose a tissue-guided face creation and adaptation scheme. With the help of the state-of-the-art text-to-image diffusion model and parametric face model, we first generate an initial reference 3D face, whose biological profile aligns with the given skull. Then, with the help of tissue thickness distribution, we modify these initial faces to match the skull through a latent optimization process. The joint distribution of tissue thickness is learned on a set of skull landmarks using a collection of scanned skull-face pairs. We also develop an efficient face adaptation tool to allow users to interactively adjust tissue thickness either globally or at local regions to explore different plausible faces. Experiments conducted on a real skull-face dataset demonstrated the effectiveness of our proposed pipeline in terms of reconstruction accuracy, diversity, and stability.

3. TVCG

   

   On Optimal Sampling for Learning SDF Using MLPs Equipped with Positional Encoding

   Guying Lin^*, Lei Yang^*, Yuan Liu, Congyi Zhang, Junhui Hou, Xiaogang Jin, Taku Komura, John Keyser, and Wenping Wang

   IEEE Transactions on Visualization and Computer Graphics, Dec 2024

   (* equal contribution)

   Abs DOI arXiv

   

   Neural implicit fields, such as the neural signed distance field (SDF) of a shape, have emerged as a powerful representation for many applications, e.g., encoding a 3D shape and performing collision detection. Typically, implicit fields are encoded by Multi-layer Perceptrons (MLP) with positional encoding (PE) to capture high-frequency geometric details. However, a notable side effect of such PE-equipped MLPs is the noisy artifacts present in the learned implicit fields. While increasing the sampling rate could in general mitigate these artifacts, in this paper we aim to explain this adverse phenomenon through the lens of Fourier analysis. We devise a tool to determine the appropriate sampling rate for learning an accurate neural implicit field without undesirable side effects. Specifically, we propose a simple yet effective method to estimate the intrinsic frequency of a given network with randomized weights based on the Fourier analysis of the network’s responses. It is observed that a PE-equipped MLP has an intrinsic frequency much higher than the highest frequency component in the PE layer. Sampling against this intrinsic frequency following the Nyquist-Sannon sampling theorem allows us to determine an appropriate training sampling rate. We empirically show in the setting of SDF fitting that this recommended sampling rate is sufficient to secure accurate fitting results, while further increasing the sampling rate would not further noticeably reduce the fitting error. Training PE-equipped MLPs simply with our sampling strategy leads to performances superior to the existing methods.

4. TVCG

   

   Tooth Motion Monitoring in Orthodontic Treatment by Mobile Device-based Multi-view Stereo

   Jiaming Xie, Congyi Zhang, Guangshun Wei , Peng Wang , Guodong Wei , Wenxi Liu, Min Gu, Ping Luo, and Wenping Wang

   IEEE Transactions on Visualization and Computer Graphics, Sep 2024

   Abs DOI

   Nowadays, orthodontics has become an important part of modern personal life to assist one in improving mastication and raising self-esteem. However, the quality of orthodontic treatment still heavily relies on the empirical evaluation of experienced doctors, which lacks quantitative assessment and requires patients to visit clinics frequently for in-person examination. To resolve the aforementioned problem, we propose a novel and practical mobile device-based framework for precisely measuring tooth movement in treatment, so as to simplify and strengthen the traditional tooth monitoring process. To this end, we formulate the tooth movement monitoring task as a multi-view multi-object pose estimation problem via different views that capture multiple texture-less and severely occluded objects (i.e. teeth). Specifically, we exploit a pre-scanned 3D tooth model and a sparse set of multi-view tooth images as inputs for our proposed tooth monitoring framework. After extracting tooth contours and localizing the initial camera pose of each view from the initial configuration, we propose a joint pose estimation scheme to precisely estimate the 3D pose of each individual tooth, so as to infer their relative offsets during treatment. Furthermore, we introduce the metric of Relative Pose Bias to evaluate the individual tooth pose accuracy in a small scale. We demonstrate that our approach is capable of reaching high accuracy and efficiency as practical orthodontic treatment monitoring requires.

2023

1. ICCV 2023

   

   Surface Extraction from Neural Unsigned Distance Fields

   Congyi Zhang^*, Guying Lin^*, Lei Yang, Xin Li, Taku Komura, Scott Schaefer, John Keyser, and Wenping Wang

   In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023

   (* equal contribution)

   Abs arXiv Code Website

   

   We propose a method, named DualMesh-UDF, to extract a surface from unsigned distance functions (UDFs), encoded by neural networks, or neural UDFs. Neural UDFs are becoming increasingly popular for surface representation because of their versatility in presenting surfaces with arbitrary topologies, as opposed to the signed distance function that is limited to representing a closed surface. However, the applications of neural UDFs are hindered by the notorious difficulty in extracting the target surfaces they represent. Recent methods for surface extraction from a neural UDF suffer from significant geometric errors or topological artifacts due to two main difficulties: (1) A UDF does not exhibit sign changes; and (2) A neural UDF typically has substantial approximation errors. DualMesh-UDF addresses these two difficulties. Specifically, given a neural UDF encoding a target surface S to be recovered, we first estimate the tangent planes of S at a set of sample points close to S. Next, we organize these sample points into local clusters, and for each local cluster, solve a linear least squares problem to determine a final surface point. These surface points are then connected to create the output mesh surface, which approximates the target surface. The robust estimation of the tangent planes of the target surface and the subsequent minimization problem constitute our core strategy, which contributes to the favorable performance of DualMesh-UDF over other competing methods. To efficiently implement this strategy, we employ an adaptive Octree. Within this framework, we estimate the location of a surface point in each of the octree cells identified as containing part of the target surface. Extensive experiments show that our method outperforms existing methods in terms of surface reconstruction quality while maintaining comparable computational efficiency.

2. ICCV 2023

   

   Batch-based Model Registration for Fast 3D Sherd Reconstruction

   Jiepeng Wang, Congyi Zhang , Peng Wang, Xin Li, Peter J. Cobb, Christian Theobalt, and Wenping Wang

   In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023

   Abs arXiv Code Website

   

   3D reconstruction techniques have widely been used for digital documentation of archaeological fragments. However, efficient digital capture of fragments remains as a challenge. In this work, we aim to develop a portable, high-throughput, and accurate reconstruction system for efficient digitization of fragments excavated in archaeological sites. To realize high-throughput digitization of large numbers of objects, an effective strategy is to perform scanning and reconstruction in batches. However, effective batch-based scanning and reconstruction face two key challenges: 1) how to correlate partial scans of the same object from multiple batch scans, and 2) how to register and reconstruct complete models from partial scans that exhibit only small overlaps. To tackle these two challenges, we develop a new batch-based matching algorithm that pairs the front and back sides of the fragments, and a new Bilateral Boundary ICP algorithm that can register partial scans sharing very narrow overlapping regions. Extensive validation in labs and testing in excavation sites demonstrate that these designs enable efficient batch-based scanning for fragments. We show that such a batch-based scanning and reconstruction pipeline can have immediate applications on digitizing sherds in archaeological excavations.

2022

1. SIGGRAPH ASIA 2022

   

   An Implicit Parametric Morphable Dental Model

   Congyi Zhang, Mohamed Elgharib, Gereon Fox, Min Gu, Christian Theobalt, and Wenping Wang

   ACM Trans. Graph., Dec 2022

   Abs DOI arXiv Code Website

   

   3D Morphable models of the human body capture variations among subjects and are useful in reconstruction and editing applications. Current dental models use an explicit mesh scene representation and model only the teeth, ignoring the gum. In this work, we present the first parametric 3D morphable dental model for both teeth and gum. Our model uses an implicit scene representation and is learned from rigidly aligned scans. It is based on a component-wise representation for each tooth and the gum, together with a learnable latent code for each of such components. It also learns a template shape thus enabling several applications such as segmentation, interpolation and tooth replacement. Our reconstruction quality is on par with the most advanced global implicit representations while enabling novel applications.

2. TVCG

   

   CreatureShop: Interactive 3D Character Modeling and Texturing from a Single Color Drawing

   Congyi Zhang, Lei Yang, Nenglun Chen, Nicholas Vining, Alla Sheffer, Francis C.M. Lau , Guoping Wang, and Wenping Wang

   IEEE Transactions on Visualization and Computer Graphics, Dec 2022

   Abs arXiv Website

   

   Creating 3D shapes from 2D drawings is an important problem with applications in content creation for computer animation and virtual reality. We introduce a new sketch-based system, CreatureShop, that enables amateurs to create high-quality textured 3D character models from 2D drawings with ease and efficiency. CreatureShop takes an input bitmap drawing of a character (such as an animal or other creature), depicted from an arbitrary descriptive pose and viewpoint, and creates a 3D shape with plausible geometric details and textures from a small number of user annotations on the 2D drawing. Our key contributions are a novel oblique view modeling method, a set of systematic approaches for producing plausible textures on the invisible or occluded parts of the 3D character (as viewed from the direction of the input drawing), and a user-friendly interactive system. We validate our system and methods by creating numerous 3D characters from various drawings, and compare our results with related works to show the advantages of our method. We perform a user study to evaluate the usability of our system, which demonstrates that our system is a practical and efficient approach to create fully-textured 3D character models for novice users.

2021

1. CHI 2021

   

   HandPainter - 3D Sketching in VR with Hand-Based Physical Proxy

   Ying Jiang, Congyi Zhang^†, Hongbo Fu, Alberto Cannavò, Fabrizio Lamberti , Henry Y K Lau, and Wenping Wang

   In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, Yokohama, Japan, Dec 2021

   († corresponding author)

   Abs DOI Website

   

   3D sketching in virtual reality (VR) enables users to create 3D virtual objects intuitively and immersively. However, previous studies showed that mid-air drawing may lead to inaccurate sketches. To address this issue, we propose to use one hand as a canvas proxy and the index finger of the other hand as a 3D pen. To this end, we first perform a formative study to compare two-handed interaction with tablet-pen interaction for VR sketching. Based on the findings of this study, we design HandPainter, a VR sketching system which focuses on the direct use of two hands for 3D sketching without requesting any tablet, pen, or VR controller. Our implementation is based on a pair of VR gloves, which provide hand tracking and gesture capture. We devise a set of intuitive gestures to control various functionalities required during 3D sketching, such as canvas panning and drawing positioning. We show the effectiveness of HandPainter by presenting a number of sketching results and discussing the outcomes of a user study-based comparison with mid-air drawing and tablet-based sketching tools.

2. Anthropometric accuracy of three-dimensional average faces compared to conventional facial measurements

   Zhiyi Shan, Richard Tai-Chiu Hsung, Congyi Zhang, Juanjuan Ji, Wing Shan Choi, Wenping Wang, Yanqi Yang, Min Gu, and Balvinder S Khambay

   Scientific Reports, Dec 2021

   Abs

   This study aimed to evaluate and compare the accuracy of average faces constructed by different methods. Original three-dimensional facial images of 26 adults in Chinese ethnicity were imported into Di3DView and MorphAnalyser for image processing. Six average faces (Ave_D15, Ave_D24, Ave_MG15, Ave_MG24, Ave_MO15, Ave_MO24) were constructed using “surface-based registration” method with different number of landmarks and template meshes. Topographic analysis was performed, and the accuracy of six average faces was assessed by linear and angular parameters in correspondence with arithmetic means calculated from individual original images. Among the six average faces constructed by the two systems, Ave_MG15 had the highest accuracy in comparison with the conventional method, while Ave_D15 had the least accuracy. Other average faces were comparable regarding the number of discrepant parameters with clinical significance. However, marginal and non-registered areas were the most inaccurate regions using Di3DView. For MorphAnalyser, the type of template mesh had an effect on the accuracy of the final 3D average face, but additional landmarks did not improve the accuracy. This study highlights the importance of validating software packages and determining the degree of accuracy, as well as the variables which may affect the result.

3. Homography-guided stereo matching for wide-baseline image interpolation

   Yuan Chang, Congyi Zhang, Yisong Chen , and Guoping Wang

   Computational Visual Media, Dec 2021

   Abs

   

   Image interpolation has a wide range of applications such as frame rate-up conversion and free viewpoint TV. Despite significant progresses, it remains an open challenge especially for image pairs with large displacements. In this paper, we first propose a novel optimization algorithm for motion estimation, which combines the advantages of both global optimization and a local parametric transformation model. We perform optimization over dynamic label sets, which are modified after each iteration using the prior of piecewise consistency to avoid local minima. Then we apply it to an image interpolation framework including occlusion handling and intermediate image interpolation. We validate the performance of our algorithm experimentally, and show that our approach achieves state-of-the-art performance.

2020

1. IEEE VR 2020

   

   DGaze: CNN-Based Gaze Prediction in Dynamic Scenes

   Zhiming Hu , Sheng Li, Congyi Zhang, Kangrui Yi , Guoping Wang, and Dinesh Manocha

   IEEE Transactions on Visualization and Computer Graphics, May 2020

   Abs DOI Website

   

   We conduct novel analyses of users’ gaze behaviors in dynamic virtual scenes and, based on our analyses, we present a novel CNN-based model called DGaze for gaze prediction in HMD-based applications. We first collect 43 users’ eye tracking data in 5 dynamic scenes under free-viewing conditions. Next, we perform statistical analysis of our data and observe that dynamic object positions, head rotation velocities, and salient regions are correlated with users’ gaze positions. Based on our analysis, we present a CNN-based model (DGaze) that combines object position sequence, head velocity sequence, and saliency features to predict users’ gaze positions. Our model can be applied to predict not only realtime gaze positions but also gaze positions in the near future and can achieve better performance than prior method. In terms of realtime prediction, DGaze achieves a 22.0% improvement over prior method in dynamic scenes and obtains an improvement of 9.5% in static scenes, based on using the angular distance as the evaluation metric. We also propose a variant of our model called DGaze_ET that can be used to predict future gaze positions with higher precision by combining accurate past gaze data gathered using an eye tracker. We further analyze our CNN architecture and verify the effectiveness of each component in our model. We apply DGaze to gaze-contingent rendering and a game, and also present the evaluation results from a user study.

2. SIGGRAPH ASIA 2020

   

   CPPM: Chi-Squared Progressive Photon Mapping

   Zehui Lin , Sheng Li, Xinlu Zeng, Congyi Zhang, Jinzhu Jia , Guoping Wang, and Dinesh Manocha

   ACM Trans. Graph., Nov 2020

   Abs DOI Website

   

   We present a novel chi-squared progressive photon mapping algorithm (CPPM) that constructs an estimator by controlling the bandwidth to obtain superior image quality. Our estimator has parametric statistical advantages over prior nonparametric methods. First, we show that when a probability density function of the photon distribution is subject to uniform distribution, the radiance estimation is unbiased under certain assumptions. Next, the local photon distribution is evaluated via a chi-squared test to determine whether the photons follow the hypothesized distribution (uniform distribution) or not. If the statistical test deems that the photons inside the bandwidth are uniformly distributed, bandwidth reduction should be suspended. Finally, we present a pipeline with a bandwidth retention and conditional reduction scheme according to the test results. This pipeline not only accumulates sufficient photons for a reliable chi-squared test, but also guarantees that the estimate converges to the correct solution under our assumptions. We evaluate our method on various benchmarks and observe significant improvement in the running time and rendering quality in terms of mean squared error over prior progressive photon mapping methods.

2019

1. SMI 2019

   

   Real-time editing of man-made mesh models under geometric constraints

   Congyi Zhang, Lei Yang, Liyou Xu , Guoping Wang, and Wenping Wang

   Computers & Graphics, Nov 2019

   Abs DOI

   

   Editing man-made mesh models under multiple geometric constraints is a crucial need for product design to facilitate design exploration and iterative optimization. However, the presence of multiple geometric constraints (e.g. the radius of a cylindrical shape, distance from a point to a plane) as well as the high dimensionality of the discrete mesh representation of man-made models make it difficult to solve this constraint system in real-time. In this paper, we propose an approach based on subspace decomposition to achieve this goal. When a set of variables are edited by the user, the proposed method minimizes the residual of the constraint system in a least square sense to derive a new shape. The resulting shape shall comply with the assigned (extrinsic) constraints while maintaining the original (intrinsic) constraints analyzed from the given mesh model. In particular, we extract a meaningful subspace of the entire solution space based on the user’s edits to reduce the order of the problem, and solve the constraint system globally in real-time. Finally, we project the approximate solution back to the original solution space to obtain the editing result.

2. IEEE VR 2019

   

   SGaze: A Data-Driven Eye-Head Coordination Model for Realtime Gaze Prediction

   Zhiming Hu, Congyi Zhang , Sheng Li , Guoping Wang, and Dinesh Manocha

   IEEE Transactions on Visualization and Computer Graphics, May 2019

   Abs DOI Website

   

   We present a novel, data-driven eye-head coordination model that can be used for realtime gaze prediction for immersive HMD-based applications without any external hardware or eye tracker. Our model (SGaze) is computed by generating a large dataset that corresponds to different users navigating in virtual worlds with different lighting conditions. We perform statistical analysis on the recorded data and observe a linear correlation between gaze positions and head rotation angular velocities. We also find that there exists a latency between eye movements and head movements. SGaze can work as a software-based realtime gaze predictor and we formulate a time related function between head movement and eye movement and use that for realtime gaze position prediction. We demonstrate the benefits of SGaze for gaze-contingent rendering and evaluate the results with a user study.