Searcharxiv⌕ Search

arXiv subjects

Hao Pan

Publications and source records attributed to Hao Pan.

At least 55 records · Page 3Linked to original sources
arXiv2024

DiffCSG: Differentiable CSG via Rasterization

Differentiable rendering is a key ingredient for inverse rendering and machine learning, as it allows to optimize scene parameters (shape, materials, lighting) to best fit target images. Differentiable rendering requires that each scene parameter relates to pixel values through differentiable operations. While 3D mesh rendering algorithms have been implemented in a differentiable way, these algorithms do not directly extend to Constructive-Solid-Geometry (CSG), a popular parametric representation of shapes, because the underlying boolean operations are typically performed with complex black-box mesh-processing libraries. We present an algorithm, DiffCSG, to render CSG models in a differentiable manner. Our algorithm builds upon CSG rasterization, which displays the result of boolean operations between primitives without explicitly computing the resulting mesh and, as such, bypasses black-box mesh processing. We describe how to implement CSG rasterization within a differentiable rendering pipeline, taking special care to apply antialiasing along primitive intersections to obtain gradients in such critical areas. Our algorithm is simple and fast, can be easily incorporated into modern machine learning setups, and enables a range of applications for computer-aided design, including direct and image-based editing of CSG primitives. Code and data: https://yyyyyhc.github.io/DiffCSG/.

cs.GR↗
arXiv2024

Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling

We present a novel unified framework that concurrently tackles recognition and future prediction for human hand pose and action modeling. Previous works generally provide isolated solutions for either recognition or prediction, which not only increases the complexity of integration in practical applications, but more importantly, cannot exploit the synergy of both sides and suffer suboptimal performances in their respective domains. To address this problem, we propose a generative Transformer VAE architecture to model hand pose and action, where the encoder and decoder capture recognition and prediction respectively, and their connection through the VAE bottleneck mandates the learning of consistent hand motion from the past to the future and vice versa. Furthermore, to faithfully model the semantic dependency and different temporal granularity of hand pose and action, we decompose the framework into two cascaded VAE blocks: the first and latter blocks respectively model the short-span poses and long-span action, and are connected by a mid-level feature representing a sub-second series of hand poses. This decomposition into block cascades facilitates capturing both short-term and long-term temporal regularity in pose and action modeling, and enables training two blocks separately to fully utilize datasets with annotations of different temporal granularities. We train and evaluate our framework across multiple datasets; results show that our joint modeling of recognition and prediction improves over isolated solutions, and that our semantic and temporal hierarchy facilitates long-term pose and action modeling.

cs.CV↗
arXiv2024

An Efficient Two-Dimensional Functional Mixed-Effect Model Framework for Repeatedly Measured Functional Data

With the rapid development of wearable device technologies, accelerometers can record minute-by-minute physical activity for consecutive days, which provides important insight into a dynamic association between the intensity of physical activity and mental health outcomes for large-scale population studies. Using Shanghai school adolescent cohort we estimate the effect of health assessment results on physical activity profiles recorded by accelerometers throughout a week, which is recognized as repeatedly measured functional data. To achieve this goal, we propose an innovative two-dimensional functional mixed-effect model (2dFMM) for the specialized data, which smoothly varies over longitudinal day observations with covariate-dependent mean and covariance functions. The modeling framework characterizes the longitudinal and functional structures while incorporating two-dimensional fixed effects for covariates of interest. We also develop a fast three-stage estimation procedure to provide accurate fixed-effect inference for model interpretability and improve computational efficiency when encountering large datasets. We find strong evidence of intraday and interday varying significant associations between physical activity and mental health assessments among our cohort population, which shed light on possible intervention strategies targeting daily physical activity patterns to improve school adolescent mental health. Our method is also used in environmental data to illustrate the wide applicability. Supplementary materials for this article are available online.

stat.ME↗
arXiv2024

Vinogradov three prime theorem with Piatetski-Shapiro primes

We prove that, for any $c_1,c_2,c_3\in(1,41/35)$, every sufficiently large odd number $N$ can be represented as the sum of three primes $N = p_1 + p_2 +p_3$ such that $p_i = \lfloor n_{i}^{c_i}\rfloor$ for some $n_i \in{\mathbb N}$ for each $1 \leq i \leq 3$. Our arguments are based on a variant of Green's transference principle due to Matomäki, Maynard and Shao. We prove a necessary restriction estimate using Bourgain's strategy and employ Harman's sieve method to optimize our upper bound for $c_i$.

math.NT↗
arXiv2024

PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction

Reverse engineering CAD models from raw geometry is a classic but challenging research problem. In particular, reconstructing the CAD modeling sequence from point clouds provides great interpretability and convenience for editing. To improve upon this problem, we introduce geometric guidance into the reconstruction network. Our proposed model, PS-CAD, reconstructs the CAD modeling sequence one step at a time. At each step, we provide two forms of geometric guidance. First, we provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. This helps the framework to focus on regions that still need work. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces where a CAD extrusion step could be started. Our framework has three major components. Geometric guidance computation extracts the two types of geometric guidance. Single-step reconstruction computes a single candidate CAD modeling step for each provided prompt. Single-step selection selects among the candidate CAD modeling steps. The process continues until the reconstruction is completed. Our quantitative results show a significant improvement across all metrics. For example, on the dataset DeepCAD, PS-CAD improves upon the best published SOTA method by reducing the geometry errors (CD and HD) by 10%, and the structural error (ECD metric) by about 15%.

cs.CV↗
arXiv2024

3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining

Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore features at the masked pixels, such as colors, the existing 3D MAE works reconstruct the missing geometry only, i.e, the location of the masked points. In contrast to previous studies, we advocate that point location recovery is inessential and restoring intrinsic point features is much superior. To this end, we propose to ignore point position reconstruction and recover high-order features at masked points including surface normals and surface variations, through a novel attention-based decoder which is independent of the encoder design. We validate the effectiveness of our pretext task and decoder design using different encoder structures for 3D training and demonstrate the advantages of our pretrained networks on various point cloud analysis tasks.

cs.CV↗
arXiv2024

CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs

CAD programs are a popular way to compactly encode shapes as a sequence of operations that are easy to parametrically modify. However, without sufficient semantic comments and structure, such programs can be challenging to understand, let alone modify. We introduce the problem of semantic commenting CAD programs, wherein the goal is to segment the input program into code blocks corresponding to semantically meaningful shape parts and assign a semantic label to each block. We solve the problem by combining program parsing with visual-semantic analysis afforded by recent advances in foundational language and vision models. Specifically, by executing the input programs, we create shapes, which we use to generate conditional photorealistic images to make use of semantic annotators for such images. We then distill the information across the images and link back to the original programs to semantically comment on them. Additionally, we collected and annotated a benchmark dataset, CADTalk, consisting of 5,288 machine-made programs and 45 human-made programs with ground truth semantic comments. We extensively evaluated our approach, compared it to a GPT-based baseline, and an open-set shape segmentation baseline, and reported an 83.24% accuracy on the new CADTalk dataset. Code and data: https://enigma-li.github.io/CADTalk/.

cs.CV↗
arXiv2024

The restricted sumsets in finite abelian groups

Suppose that $k\geq 2$ and $A$ is a non-empty subset of a finite abelian group $G$ with $|G|>1$. Then the cardinality of the restricted sumset $$ k^\wedge A:=\{a_1+\cdots+a_k:\,a_1,\ldots,a_k\in A,\ a_i\neq a_j\text{ for }i\neq j\} $$ is at least $$ \min\{p(G), k|A|-k^2+1\}, $$ where $p(G)$ denotes the least prime divisor of $|G|$.

math.CO↗
arXiv2024

Nonreciprocal Pancharatnam-Berry Metasurface for Unidirectional Wavefront Manipulation

Optical metasurfaces have been widely used for manipulating electromagnetic waves due to their low intrinsic loss and easy fabrication. The metasurfaces employing the Pancharatnam-Berry (PB) geometric phase, called PB metasurfaces, have been extensively applied to realize spin-dependent functionalities, such as beam steering, focusing, holography, etc. The demand for PB metasurfaces in complex environments has brought about one challenging problem, i.e., the interference of multiple wave channels that limits the performance of PB metasurfaces. A promising solution is developing nonreciprocal PB metasurfaces that can isolate undesired wave channels and exhibit unidirectional functionalities. Here, we propose a mechanism to realize nonreciprocal PB metasurfaces of subwavelength thickness by using the magneto-optical effect of YIG material in synergy with the PB geometric phase of spatially rotating meta-atoms. Using full-wave numerical simulations, we show that the metasurface composed of dielectric cylinders and a thin YIG layer can achieve nearly 92% and 81% isolation of circularly polarized lights at 5.5 GHz and 6.5 GHz, respectively, attributed to the enhancement of the magneto-optical effect by the resonant Mie modes and Fabry-Pérot cavity mode. In addition, the metasurface can enable efficient unidirectional wavefront manipulations of circularly polarized lights, including nonreciprocal beam steering and nonreciprocal beam focusing. The proposed metasurface can find highly useful applications in optical communications, optical sensing, and quantum information processing.

physics.optics↗
arXiv2024

MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion

As a promising 3D generation technique, multiview diffusion (MVD) has received a lot of attention due to its advantages in terms of generalizability, quality, and efficiency. By finetuning pretrained large image diffusion models with 3D data, the MVD methods first generate multiple views of a 3D object based on an image or text prompt and then reconstruct 3D shapes with multiview 3D reconstruction. However, the sparse views and inconsistent details in the generated images make 3D reconstruction challenging. We present MVD$^2$, an efficient 3D reconstruction method for multiview diffusion (MVD) images. MVD$^2$ aggregates image features into a 3D feature volume by projection and convolution and then decodes volumetric features into a 3D mesh. We train MVD$^2$ with 3D shape collections and MVD images prompted by rendered views of 3D shapes. To address the discrepancy between the generated multiview images and ground-truth views of the 3D shapes, we design a simple-yet-efficient view-dependent training scheme. MVD$^2$ improves the 3D generation quality of MVD and is fast and robust to various MVD methods. After training, it can efficiently decode 3D meshes from multiview images within one second. We train MVD$^2$ with Zero-123++ and ObjectVerse-LVIS 3D dataset and demonstrate its superior performance in generating 3D models from multiview images generated by different MVD methods, using both synthetic and real images as prompts.

cs.CV↗
arXiv2024

Mastering the Game of Guandan with Deep Reinforcement Learning and Behavior Regulating

Games are a simplified model of reality and often serve as a favored platform for Artificial Intelligence (AI) research. Much of the research is concerned with game-playing agents and their decision making processes. The game of Guandan (literally, "throwing eggs") is a challenging game where even professional human players struggle to make the right decision at times. In this paper we propose a framework named GuanZero for AI agents to master this game using Monte-Carlo methods and deep neural networks. The main contribution of this paper is about regulating agents' behavior through a carefully designed neural network encoding scheme. We then demonstrate the effectiveness of the proposed framework by comparing it with state-of-the-art approaches.

cs.AI↗
arXiv2023

Large Language Models Empowered Autonomous Edge AI for Connected Intelligence

The evolution of wireless networks gravitates towards connected intelligence, a concept that envisions seamless interconnectivity among humans, objects, and intelligence in a hyper-connected cyber-physical world. Edge artificial intelligence (Edge AI) is a promising solution to achieve connected intelligence by delivering high-quality, low-latency, and privacy-preserving AI services at the network edge. This article presents a vision of autonomous edge AI systems that automatically organize, adapt, and optimize themselves to meet users' diverse requirements, leveraging the power of large language models (LLMs), i.e., Generative Pretrained Transformer (GPT). By exploiting the powerful abilities of GPT in language understanding, planning, and code generation, as well as incorporating classic wisdom such as task-oriented communication and edge federated learning, we present a versatile framework that efficiently coordinates edge AI models to cater to users' personal demands while automatically generating code to train new models in a privacy-preserving manner. Experimental results demonstrate the system's remarkable ability to accurately comprehend user demands, efficiently execute AI models with minimal cost, and effectively create high-performance AI models at edge servers.

cs.IT↗
arXiv2023

iPUNet:Iterative Cross Field Guided Point Cloud Upsampling

Point clouds acquired by 3D scanning devices are often sparse, noisy, and non-uniform, causing a loss of geometric features. To facilitate the usability of point clouds in downstream applications, given such input, we present a learning-based point upsampling method, i.e., iPUNet, which generates dense and uniform points at arbitrary ratios and better captures sharp features. To generate feature-aware points, we introduce cross fields that are aligned to sharp geometric features by self-supervision to guide point generation. Given cross field defined frames, we enable arbitrary ratio upsampling by learning at each input point a local parameterized surface. The learned surface consumes the neighboring points and 2D tangent plane coordinates as input, and maps onto a continuous surface in 3D where arbitrary ratios of output points can be sampled. To solve the non-uniformity of input points, on top of the cross field guided upsampling, we further introduce an iterative strategy that refines the point distribution by moving sparse points onto the desired continuous 3D surface in each iteration. Within only a few iterations, the sparse points are evenly distributed and their corresponding dense samples are more uniform and better capture geometric features. Through extensive evaluations on diverse scans of objects and scenes, we demonstrate that iPUNet is robust to handle noisy and non-uniformly distributed inputs, and outperforms state-of-the-art point cloud upsampling methods.

cs.CV↗
arXiv2023

Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding

The use of pretrained backbones with fine-tuning has been successful for 2D vision and natural language processing tasks, showing advantages over task-specific networks. In this work, we introduce a pretrained 3D backbone, called {\SST}, for 3D indoor scene understanding. We design a 3D Swin transformer as our backbone network, which enables efficient self-attention on sparse voxels with linear memory complexity, making the backbone scalable to large models and datasets. We also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network performance. We pretrained a large {\SST} model on a synthetic Structured3D dataset, which is an order of magnitude larger than the ScanNet dataset. Our model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3D point datasets, but also outperforms state-of-the-art methods on downstream tasks with +2.3 mIoU and +2.2 mIoU on S3DIS Area5 and 6-fold semantic segmentation, +1.8 mIoU on ScanNet segmentation (val), +1.9 mAP@0.5 on ScanNet detection, and +8.1 mAP@0.5 on S3DIS detection. A series of extensive ablation studies further validate the scalability, generality, and superior performance enabled by our approach. The code and models are available at https://github.com/microsoft/Swin3D .

cs.CV↗
arXiv2023

Manipulating chiral-spin transport with ferroelectric polarization

A collective excitation of the spin structure in a magnetic insulator can transmit spin-angular momentum with negligible dissipation. This quantum of a spin wave, introduced more than nine decades ago, has always been manipulated through magnetic dipoles, (i.e., timereversal symmetry). Here, we report the experimental observation of chiral-spin transport in multiferroic BiFeO3, where the spin transport is controlled by reversing the ferroelectric polarization (i.e., spatial inversion symmetry). The ferroelectrically controlled magnons produce an unprecedented ratio of up to 18% rectification at room temperature. The spin torque that the magnons in BiFeO3 carry can be used to efficiently switch the magnetization of adja-cent magnets, with a spin-torque efficiency being comparable to the spin Hall effect in heavy metals. Utilizing such a controllable magnon generation and transmission in BiFeO3, an alloxide, energy-scalable logic is demonstrated composed of spin-orbit injection, detection, and magnetoelectric control. This observation opens a new chapter of multiferroic magnons and paves an alternative pathway towards low-dissipation nanoelectronics.

physics.app-ph↗
arXiv2023

Locally Attentional SDF Diffusion for Controllable 3D Shape Generation

Although the recent rapid evolution of 3D generative neural networks greatly improves 3D shape generation, it is still not convenient for ordinary users to create 3D shapes and control the local geometry of generated shapes. To address these challenges, we propose a diffusion-based 3D generation framework -- locally attentional SDF diffusion, to model plausible 3D shapes, via 2D sketch image input. Our method is built on a two-stage diffusion model. The first stage, named occupancy-diffusion, aims to generate a low-resolution occupancy field to approximate the shape shell. The second stage, named SDF-diffusion, synthesizes a high-resolution signed distance field within the occupied voxels determined by the first stage to extract fine geometry. Our model is empowered by a novel view-aware local attention mechanism for image-conditioned shape generation, which takes advantage of 2D image patch features to guide 3D voxel feature learning, greatly improving local controllability and model generalizability. Through extensive experiments in sketch-conditioned and category-conditioned 3D shape generation tasks, we validate and demonstrate the ability of our method to provide plausible and diverse 3D shapes, as well as its superior controllability and generalizability over existing work. Our code and trained models are available at https://zhengxinyang.github.io/projects/LAS-Diffusion.html

cs.CV↗
arXiv2023

Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos

Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit temporal information for robust estimation. Noticing the different temporal granularity of and the semantic correlation between hand pose estimation and action recognition, we build a network hierarchy with two cascaded transformer encoders, where the first one exploits the short-term temporal cue for hand pose estimation, and the latter aggregates per-frame pose and object information over a longer time span to recognize the action. Our approach achieves competitive results on two first-person hand action benchmarks, namely FPHA and H2O. Extensive ablation studies verify our design choices.

cs.CV↗