Zherong Pan

Zherong Pan

Auto-generated profile, based on publicly available information

Zherong Pan

LightSpeed Studios

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 January 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
QTQingyang Tan
Qingyang Tan
ZPZherong Pan
Zherong Pan
LGLin Gao
Lin Gao
DMDinesh Manocha
Dinesh Manocha
We address the problem of accelerating thin-shell deformable object simulations by dimension reduction. We present a new algorithm to embed a high-dimensional configuration space of deformable objects in a low-dimensional feature space, where the configurations of objects and feature points have approximate one-to-one mapping. Our key technique is a graph-based convolutional neural network (CNN) defined on meshes with arbitrary topologies and a new mesh embedding approach based on physics-inspired loss term. We have applied our approach to accelerate high-resolution thin shell simulations corresponding to cloth-like materials, where the configuration space has tens of thousands of degrees of freedom. We show that our physics-inspired embedding approach leads to higher accuracy compared with prior mesh embedding methods. Finally, we show that the temporal evolution of the mesh in the feature space can also be learned using a recurrent neural network (RNN) leading to fully learnable physics simulators. After training our learned simulator runs 500-10000× faster and the accuracy is high enough for robot manipulation tasks.

15 September 2022 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
ZPZherong Pan
Zherong Pan
AZAndy Zeng
Andy Zeng
YLYunzhu Li
Yunzhu Li
Jingjin YuJingjin Yu
Jingjin Yu
KHKris Hauser
Kris Hauser
Robot manipulation of multiple objects is an important topic for applications including warehouse automation, service robots performing cleaning, and large-scale object sorting. Although problems can range in complexity from a few objects to large disordered piles, autonomy remains a significant technical challenge due to the high-dimensional joint configuration space of the robot and all objects, the complex dynamics of object interaction, and the ambiguity and occlusion caused by clutter. This article surveys a broad range of classical and state-of-the-art research in multiobject manipulation and categorizes them along the dimensions of tasks, perception, predictive models, and decision-making algorithms. It also covers emerging trends and open problems faced in the ongoing effort to realize robust multiobject manipulation systems in practice.

26 July 2023 in ACM Transactions on Graphics
Verified
Journal Article
Open access
ZCZhen Chen
Zhen Chen
ZPZherong Pan
Zherong Pan
KWKui Wu
Kui Wu
EVEtienne Vouga
Etienne Vouga
XGXifeng Gao
Xifeng Gao
We propose a robust re-meshing approach that can automatically generate visual-preserving low-poly meshes for any high-poly models found in the wild. Our method can be seamlessly integrated into current mesh-based 3D asset production pipelines. Given an input high-poly, our method proceeds in two stages: 1) Robustly extracting an offset surface mesh that is feature-preserving, and guaranteed to be watertight, manifold, and self-intersection free; 2) Progressively simplifying and flowing the offset mesh to bring it close to the input. The simplicity and the visual-preservation of the generated low-poly is controlled by a user-required target screen size of the input: decreasing the screen size reduces the element count of the low-poly but enlarges its visual difference from the input. We have evaluated our method on a subset of the Thingi10K dataset that contains models created by practitioners in different domains, with varying topological and geometric complexities. Compared to state-of-the-art approaches and widely used software, our method demonstrates its superiority in terms of the element count, visual preservation, geometry, and topology guarantees of the generated low-polys.

26 July 2023 in ACM Transactions on Graphics
Verified
Journal Article
Open access
JHJerry Hsu
Jerry Hsu
TWTongtong Wang
Tongtong Wang
ZPZherong Pan
Zherong Pan
XGXifeng Gao
Xifeng Gao
CYCem Yuksel
Cem Yuksel
KWKui Wu
Kui Wu
Lagrangian/Eulerian hybrid strand-based hair simulation techniques have quickly become a popular approach in VFX and real-time graphics applications. With Lagrangian hair dynamics, the inter-hair contacts are resolved in the Eulerian grid using the continuum method, i.e., the MPM scheme with the granular Drucker-Prager rheology, to avoid expensive collision detection and handling. This fuzzy collision handling makes the authoring process significantly easier. However, although current hair grooming tools provide a wide range of strand-based modeling tools for this simulation approach, the crucial sag-free initialization functionality remains often ignored. Thus, when the simulation starts, gravity would cause any artistic hairstyle to sag and deform into unintended and undesirable shapes. This paper proposes a novel four-stage sag-free initialization framework to solve stable quasistatic configurations for hybrid strand-based hair dynamic systems. These four stages are split into two global-local pairs. The first one ensures static equilibrium at every Eulerian grid node with additional inequality constraints to prevent stress from exiting the yielding surface. We then derive several associated closed-form solutions in the local stage to compute segment rest lengths, orientations, and particle deformation gradients in parallel. The second global-local step solves along each hair strand to ensure all the bend and twist constraints produce zero net torque on every hair segment, followed by a local step to adjust the rest Darboux vectors to a unit quaternion. We also introduce an essential modification for the Darboux vector to eliminate the ambiguity of the Cosserat rod rest pose in both initialization and simulation. We evaluate our method on a wide range of hairstyles, and our approach can only take a few seconds to minutes to get the rest quasistatic configurations for hundreds of hair strands. Our results show that our method successfully prevents sagging and has minimal impact on the hair motion during simulation.

28 September 2023 in ACM Transactions on Graphics
Verified
Journal Article
Open access
JKJulian Knodt
Julian Knodt
ZPZherong Pan
Zherong Pan
KWKui Wu
Kui Wu
XGXifeng Gao
Xifeng Gao
Level of detail has been widely used in interactive computer graphics. In current industrial 3D modeling pipelines, artists rely on commercial software to generate highly detailed models with UV maps and then bake textures for low-poly counterparts. In these pipelines, each step is performed separately, leading to unsatisfactory visual appearances for low polygon count models. Moreover, existing texture baking techniques assume the low-poly mesh has a small geometric difference from the high-poly, which is often not true in practice, especially with extremely low poly count models. To alleviate the visual discrepancy of the low-poly mesh, we propose to jointly optimize UV mappings during texture baking, allowing for low-poly models to faithfully replicate the appearance of the high-poly even with large geometric differences. We formulate the optimization within a differentiable rendering framework, allowing the automatic adjustment of texture regions to encode appearance information. To compensate for view parallax when two meshes have large geometric differences, we introduce a spherical harmonic parallax mapping, which uses spherical harmonic functions to modulate per-texel UV coordinates based on the view direction. We evaluate the effectiveness and robustness of our approach on a dataset composed of online downloaded models, with varying complexities and geometric discrepancies. Our method achieves superior quality over state-of-the-art techniques and commercial solutions.

28 July 2023 in ACM Transactions on Graphics
Verified
Journal Article
Open access
HZHang Zhao
Hang Zhao
ZPZherong Pan
Zherong Pan
YYYang Yu
Yang Yu
Kai XuKai Xu
Kai Xu
We study the problem of learning online packing skills for irregular 3D shapes , which is arguably the most challenging setting of bin packing problems. The goal is to consecutively move a sequence of 3D objects with arbitrary shapes into a designated container with only partial observations of the object sequence. We take physical realizability into account, involving physics dynamics and constraints of a placement. The packing policy should understand the 3D geometry of the object to be packed and make effective decisions to accommodate it in the container in a physically realizable way. We propose a Reinforcement Learning (RL) pipeline to learn the policy. The complex irregular geometry and imperfect object placement together lead to huge solution space. Direct training in such space is prohibitively data intensive. We instead propose a theoretically provable method for candidate action generation to reduce the action space of RL and the learning burden. A parameterized policy is then learned to select the best placement from the candidates. Equipped with an efficient method of asynchronous RL acceleration and a data preparation process of simulation-ready training sequences, a mature packing policy can be trained in a physics-based environment within 48 hours. Through extensive evaluation on a variety of real-life shape datasets and comparisons with state-of-the-art baselines, we demonstrate that our method outperforms the best-performing baseline on all datasets by at least 12.8% in terms of packing utility. We also release our datasets and source code to support further research in this direction. 1