arXiv subjects

Shilin Zhu

Publications and source records attributed to Shilin Zhu.

14 recordsLinked to original sources

arXiv2026

PatchScene: Patch-based Voxel Diffusion for Large-Scale Scene Completion

We propose PatchScene, a novel diffusion-based framework for large-scale LiDAR scene completion. Unlike existing methods that rely on global latent representations or dense voxel grids, PatchScene adopts a patch-based voxel diffusion paradigm that explicitly generates fine-grained geometry within localized 3D regions. To ensure coherent reconstruction at both spatial and temporal scales, we introduce a confidence-guided spatio-temporal fusion mechanism that integrates overlapping patches and adjacent frames in a unified generative process. Furthermore, we design an Annular-Flow diffusion strategy that leverages the radial density pattern of LiDAR scans to progressively propagate high-fidelity information from near-range to far-range regions, enabling spatially unbounded scene completion. Extensive experiments on the SemanticKITTI benchmark demonstrate that PatchScene achieves state-of-the-art performance across all standard metrics, surpassing previous approaches in both geometric accuracy and temporal consistency. Remarkably, the model trained on 20 m LiDAR ranges generalizes effectively to 50 m scenes without retraining, highlighting its strong scalability and generalization capability for real-world autonomous driving applications.

cs.CV↗

arXiv2025

Bridging the genotype-phenotype gap with generative artificial intelligence

The genotype-phenotype gap is a persistent barrier to complex trait genetic dissection, worsened by the explosive growth of genomic data (1.5 billion variants identified in the UK Biobank WGS study) alongside persistently scarce and subjective human-defined phenotypes. Digital phenotyping offers a potential solution, yet existing tools fail to balance scalable non-manual phenotype generation and biological interpretability of these quantitative traits. Here we report AIPheno, the first generative AI-driven "phenotype sequencer" that bridges this gap. It enables high-throughput, unsupervised extraction of digital phenotypes from imaging data and unlocks their biological meaning via generative network analysis. AIPheno transforms imaging modalities into a rich source of quantitative traits, dramatically enhancing cross-species genetic discovery, including novel loci such as CCBE1 (humans), KITLG-TMTC3 (domestic pigeons), and SOD2-IGF2R (swine). Critically, its generative module decodes AI-derived phenotypes by synthesizing variant-specific images to yield actionable biological insights. For example, it clarifies how the OCA2-HERC2 locus pleiotropically links pigmentation to retinal vascular traits via vascular visibility modulation. Integrating scalable non-manual phenotyping, enhanced genetic discovery power, and generative mechanistic decoding, AIPheno establishes a transformative closed-loop paradigm. This work addresses the longstanding genotype-phenotype imbalance, redefines digital phenotype utility, and accelerates translation of genetic associations into actionable understanding with profound implications for human health and agriculture.

q-bio.QM↗

arXiv2025

Absence of magnetic order and magnetic fluctuations in RuO$_{2}$

A novel magnetic class blending ferromagnetism and antiferromagnetism, termed altermagnetism, has gained significant attention for its staggered order in coordinate and momentum spaces, time-reversal symmetry-breaking phenomena, and promising applications in spintronics. Ruthenium dioxide (RuO$_{2}$) has been considered a candidate material for altermagnetism, yet the presence of magnetic moments on Ru atoms remains a subject of debate. In this study, we systematically investigated the magnetic properties of RuO$_{2}$ powder using nuclear quadrupole resonance (NQR) measurements. The NQR spectra show that there is no internal magnetic field. Furthermore, the temperature independence of spin-lattice relaxation rate, $1/T_1T$, proves that there are no magnetic fluctuations. Our results unambiguously demonstrate that Ru atoms in RuO$_{2}$ possess neither static magnetic moments nor fluctuating magnetic moments, and thus RuO$_{2}$ does not possess the magnetic characteristics essential for altermagnetism.

cond-mat.str-el↗

arXiv2023

Phases and magnetism at the microscale in compounds containing nominal Pb10-xCux(PO4)6O

Achieving superconductivity at room temperature could lead to substantial advancements in industry and technology. Recently, a compound known as Cu-doped lead-apatite, Pb10-xCux(PO4)6O (0.9 < x < 1.1), referred to as "LK-99", has been reported to exhibit unusual electrical and magnetic behaviors that appear to resemble a superconducting transition above room temperature. In this work we collected multiphase samples containing the nominal Pb10-xCux(PO4)6O phase (no superconductivity observed in our measured samples), synthesized by three independent groups, and studied their chemical, magnetic, and electrical properties at the microscale to overcome difficulties in bulk measurements. Through the utilization of optical, scanning electron, atomic force, and scanning diamond nitrogen-vacancy microscopy techniques, we are able to establish a link between local magnetic properties and specific microscale chemical phases. Our findings indicate that while the Pb10-xCux(PO4)6O phase seems to have a mixed magnetism contribution, a significant fraction of the diamagnetic response can be attributed to Cu-rich regions (e.g., Cu2S derived from a reagent used in the synthesis). Additionally, our electrical measurements reveal the phenomenon of current path switch and a change in resistance states of Cu2S. This provides a potential explanation for the electrical behavior observed in compounds related to Pb10-xCux(PO4)6O.

cond-mat.mtrl-sci↗

arXiv2023

First order transition in Pb$_{10-x}$Cu$_x$(PO$_4$)$_6$O ($0.9<x<1.1$) containing Cu$_2$S

Lee et al. reported that the compound LK99, with a chemical formula of Pb$_{10-x}$Cu$_x$(PO$_4$)$_6$O ($0.9<x<1.1$), exhibits room-temperature superconductivity under ambient pressure. In this study, we investigated the transport and magnetic properties of pure Cu$_2$S and LK-99 containing Cu$_2$S. We observed a sharp superconducting-like transition and a thermal hysteresis behavior in the resistivity and magnetic susceptibility. However, we did not observe zero-resistivity below the transition temperature. We argue that the so-called superconducting behavior in LK-99 is most likely due to a reduction in resistivity caused by the first order structural phase transition of Cu$_2$S at around 385 K, from the $β$ phase at high temperature to the $γ$ phase at low temperature.

cond-mat.supr-con↗

arXiv2020

Photon-Driven Neural Path Guiding

Although Monte Carlo path tracing is a simple and effective algorithm to synthesize photo-realistic images, it is often very slow to converge to noise-free results when involving complex global illumination. One of the most successful variance-reduction techniques is path guiding, which can learn better distributions for importance sampling to reduce pixel noise. However, previous methods require a large number of path samples to achieve reliable path guiding. We present a novel neural path guiding approach that can reconstruct high-quality sampling distributions for path guiding from a sparse set of samples, using an offline trained neural network. We leverage photons traced from light sources as the input for sampling density reconstruction, which is highly effective for challenging scenes with strong global illumination. To fully make use of our deep neural network, we partition the scene space into an adaptive hierarchical grid, in which we apply our network to reconstruct high-quality sampling distributions for any local region in the scene. This allows for highly efficient path guiding for any path bounce at any location in path tracing. We demonstrate that our photon-driven neural path guiding method can generalize well on diverse challenging testing scenes that are not seen in training. Our approach achieves significantly better rendering results of testing scenes than previous state-of-the-art path guiding methods.

cs.GR↗

arXiv2020

Survey: Machine Learning in Production Rendering

In the past few years, machine learning-based approaches have had some great success for rendering animated feature films. This survey summarizes several of the most dramatic improvements in using deep neural networks over traditional rendering methods, such as better image quality and lower computational overhead. More specifically, this survey covers the fundamental principles of machine learning and its applications, such as denoising, path guiding, rendering participating media, and other notoriously difficult light transport situations. Some of these techniques have already been used in the latest released animations while others are still in the continuing development by researchers in both academia and movie studios. Although learning-based rendering methods still have some open issues, they have already demonstrated promising performance in multiple parts of the rendering pipeline, and people are continuously making new attempts.

cs.GR↗

arXiv2020

Deep Photon Mapping

Recently, deep learning-based denoising approaches have led to dramatic improvements in low sample-count Monte Carlo rendering. These approaches are aimed at path tracing, which is not ideal for simulating challenging light transport effects like caustics, where photon mapping is the method of choice. However, photon mapping requires very large numbers of traced photons to achieve high-quality reconstructions. In this paper, we develop the first deep learning-based method for particle-based rendering, and specifically focus on photon density estimation, the core of all particle-based methods. We train a novel deep neural network to predict a kernel function to aggregate photon contributions at shading points. Our network encodes individual photons into per-photon features, aggregates them in the neighborhood of a shading point to construct a photon local context vector, and infers a kernel function from the per-photon and photon local context features. This network is easy to incorporate in many previous photon mapping methods (by simply swapping the kernel density estimator) and can produce high-quality reconstructions of complex global illumination effects like caustics with an order of magnitude fewer photons compared to previous photon mapping methods.

cs.GR↗

arXiv2020

Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness

We present Uncertainty-aware Cascaded Stereo Network (UCS-Net) for 3D reconstruction from multiple RGB images. Multi-view stereo (MVS) aims to reconstruct fine-grained scene geometry from multi-view images. Previous learning-based MVS methods estimate per-view depth using plane sweep volumes with a fixed depth hypothesis at each plane; this generally requires densely sampled planes for desired accuracy, and it is very hard to achieve high-resolution depth. In contrast, we propose adaptive thin volumes (ATVs); in an ATV, the depth hypothesis of each plane is spatially varying, which adapts to the uncertainties of previous per-pixel depth predictions. Our UCS-Net has three stages: the first stage processes a small standard plane sweep volume to predict low-resolution depth; two ATVs are then used in the following stages to refine the depth with higher resolution and higher accuracy. Our ATV consists of only a small number of planes; yet, it efficiently partitions local depth ranges within learned small intervals. In particular, we propose to use variance-based uncertainty estimates to adaptively construct ATVs; this differentiable process introduces reasonable and fine-grained spatial partitioning. Our multi-stage framework progressively subdivides the vast scene space with increasing depth resolution and precision, which enables scene reconstruction with high completeness and accuracy in a coarse-to-fine fashion. We demonstrate that our method achieves superior performance compared with state-of-the-art benchmarks on various challenging datasets.

cs.CV↗

arXiv2018

PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding

We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. Our dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories. This dataset enables and serves as a catalyst for many tasks such as shape analysis, dynamic 3D scene modeling and simulation, affordance analysis, and others. Using our dataset, we establish three benchmarking tasks for evaluating 3D part recognition: fine-grained semantic segmentation, hierarchical semantic segmentation, and instance segmentation. We benchmark four state-of-the-art 3D deep learning algorithms for fine-grained semantic segmentation and three baseline methods for hierarchical semantic segmentation. We also propose a novel method for part instance segmentation and demonstrate its superior performance over existing methods.

cs.CV↗

arXiv2018

Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?

Binary neural networks (BNN) have been studied extensively since they run dramatically faster at lower memory and power consumption than floating-point networks, thanks to the efficiency of bit operations. However, contemporary BNNs whose weights and activations are both single bits suffer from severe accuracy degradation. To understand why, we investigate the representation ability, speed and bias/variance of BNNs through extensive experiments. We conclude that the error of BNNs is predominantly caused by the intrinsic instability (training time) and non-robustness (train & test time). Inspired by this investigation, we propose the Binary Ensemble Neural Network (BENN) which leverages ensemble methods to improve the performance of BNNs with limited efficiency cost. While ensemble techniques have been broadly believed to be only marginally helpful for strong classifiers such as deep neural networks, our analyses and experiments show that they are naturally a perfect fit to boost BNNs. We find that our BENN, which is faster and much more robust than state-of-the-art binary networks, can even surpass the accuracy of the full-precision floating number network with the same architecture.

cs.LG↗

arXiv2018

Towards Fast and Energy-Efficient Binarized Neural Network Inference on FPGA

Binarized Neural Network (BNN) removes bitwidth redundancy in classical CNN by using a single bit (-1/+1) for network parameters and intermediate representations, which has greatly reduced the off-chip data transfer and storage overhead. However, a large amount of computation redundancy still exists in BNN inference. By analyzing local properties of images and the learned BNN kernel weights, we observe an average of $\sim$78% input similarity and $\sim$59% weight similarity among weight kernels, measured by our proposed metric in common network architectures. Thus there does exist redundancy that can be exploited to further reduce the amount of on-chip computations. Motivated by the observation, in this paper, we proposed two types of fast and energy-efficient architectures for BNN inference. We also provide analysis and insights to pick the better strategy of these two for different datasets and network models. By reusing the results from previous computation, much cycles for data buffer access and computations can be skipped. By experiments, we demonstrate that 80% of the computation and 40% of the buffer access can be skipped by exploiting BNN similarity. Thus, our design can achieve 17% reduction in total power consumption, 54% reduction in on-chip power consumption and 2.4$\times$ maximum speedup, compared to the baseline without applying our reuse technique. Our design also shows 1.9$\times$ more area-efficiency compared to state-of-the-art BNN inference design. We believe our deployment of BNN on FPGA leads to a promising future of running deep learning models on mobile devices.

cs.LG↗

arXiv2018

2DR: Towards Fine-Grained 2-D RFID Touch Sensing

In this paper, we introduce 2DR, a single RFID tag which can seamlessly sense two-dimensional human touch using off-the-shelf RFID readers. Instead of using a two-dimensional tag array to sense human finger touch on a surface, 2DR only uses one or two RFID chip(s), which reduces the manufacturing cost and makes the tag more suitable for printing on flexible materials. The key idea behind 2DR is to design a custom-shape antenna and classify human finger touch based on unique phase information using statistical learning. We printed 2DR tag on FR-4 substrate and use off-the-shelf UHF-RFID readers (FCC frequency band) to sense different touch activities. Experiments show great potential of our design. Moreover, 2DR can be further extended to 3D by building stereoscopic model.

eess.SP↗

arXiv2003

Chiral Symmetry in an Extended Constituent Quark Potential Model

The chiral symmetry is applied to an extended constituent quark potential model. With random phase approximation (RPA), the model comprises sea quark excitations. To obtain the pseudoscalar $π$ meson as a Goldstone boson, the quark effective potentials are modified in the model to account for the dynamical breaking of chiral symmetry. Also the vector $ρ$ meson is calculated and the KSRF relation about $π$ and $ρ$ meson decay constants is derived in the model.

hep-ph↗