arXiv subjects

Wenchao Ma

Publications and source records attributed to Wenchao Ma.

At least 19 recordsLinked to original sources

arXiv2026

A Geodesic Cut-Cell Prior for Neural Skinning

We introduce cut-cell skinning, a geometric prior designed to augment data-driven skinning weight generation. While data-driven methods show promise in producing high-quality skinning weights, they often lack the generalizability of classic geometric approaches. To bridge this gap, we propose a geometric prior that can be robustly computed for in-the-wild meshes and is efficient for large-scale machine learning workflows. The key idea of our cut-cell skinning is a fast graph-based approximation of the volumetric geodesics distances, motivated by their importance in classic skinning weight computation. Our method achieves orders of magnitude speedup compared to optimization-based solvers and remains resilient to topological artifacts common in cage- or voxel-based alternatives. We demonstrate the efficacy of the cut-cell skinning prior by integrating it into recent neural skinning models, showing consistent improvements across existing methods and achieving state-of-the-art results. Project page: https://wenchao-m.github.io/CutCell.github.io/

cs.GR↗

arXiv2026

Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering

Recent conditional video generation models have shown promising potentials to transform 3D engine renderings, such as depth maps and untextured geometry, into photorealistic videos for gaming and immersive content creation. These applications require long-horizon auto-regressive generation that continuously synthesizes new frames while preserving a persistent 3D world. Auto-regressive generators synthesize video chunk by chunk with a bounded KV cache, so when the camera revisits a location after its context has been evicted, the model often regenerates inconsistent appearance, even though the conditioning renderings (e.g., depth) remain perfectly aligned with the underlying geometry. We address this revisit inconsistency without any post-training by exploiting correspondences the 3D engine already provides: temporal correspondence retrieves pose-matched historical latent chunks into the KV cache as loop-closure memory, while spatial correspondence from camera pose and depth reprojection biases token-level attention toward geometrically corresponding regions of the retrieved chunks. We demonstrate our method on loop-closure trajectories mined from TartanAir and TartanGround dataset to mirror complicate real-world application scenarios, where it outperforms existing training-free baselines on revisit consistency without losing overall video quality. Project Page: https://wenchao-m.github.io/ClosetheLoop.github.io/

cs.CV↗

arXiv2025

RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data

In this paper, we present RigAnyFace (RAF), a scalable neural auto-rigging framework for facial meshes of diverse topologies, including those with multiple disconnected components. RAF deforms a static neutral facial mesh into industry-standard FACS poses to form an expressive blendshape rig. Deformations are predicted by a triangulation-agnostic surface learning network augmented with our tailored architecture design to condition on FACS parameters and efficiently process disconnected components. For training, we curated a dataset of facial meshes, with a subset meticulously rigged by professional artists to serve as accurate 3D ground truth for deformation supervision. Due to the high cost of manual rigging, this subset is limited in size, constraining the generalization ability of models trained exclusively on it. To address this, we design a 2D supervision strategy for unlabeled neutral meshes without rigs. This strategy increases data diversity and allows for scaled training, thereby enhancing the generalization ability of models trained on this augmented data. Extensive experiments demonstrate that RAF is able to rig meshes of diverse topologies on not only our artist-crafted assets but also in-the-wild samples, outperforming previous works in accuracy and generalizability. Moreover, our method advances beyond prior work by supporting multiple disconnected components, such as eyeballs, for more detailed expression animation. Project page: https://wenchao-m.github.io/RigAnyFace.github.io

cs.CV↗

arXiv2025

SafeTriage: Facial Video De-identification for Privacy-Preserving Stroke Triage

Effective stroke triage in emergency settings often relies on clinicians' ability to identify subtle abnormalities in facial muscle coordination. While recent AI models have shown promise in detecting such patterns from patient facial videos, their reliance on real patient data raises significant ethical and privacy challenges -- especially when training robust and generalizable models across institutions. To address these concerns, we propose SafeTriage, a novel method designed to de-identify patient facial videos while preserving essential motion cues crucial for stroke diagnosis. SafeTriage leverages a pretrained video motion transfer (VMT) model to map the motion characteristics of real patient faces onto synthetic identities. This approach retains diagnostically relevant facial dynamics without revealing the patients' identities. To mitigate the distribution shift between normal population pre-training videos and patient population test videos, we introduce a conditional generative model for visual prompt tuning, which adapts the input space of the VMT model to ensure accurate motion transfer without needing to fine-tune the VMT model backbone. Comprehensive evaluation, including quantitative metrics and clinical expert assessments, demonstrates that SafeTriage-produced synthetic videos effectively preserve stroke-relevant facial patterns, enabling reliable AI-based triage. Our evaluations also show that SafeTriage provides robust privacy protection while maintaining diagnostic accuracy, offering a secure and ethically sound foundation for data sharing and AI-driven clinical analysis in neurological disorders.

cs.CV↗

arXiv2025

Inverse design for robust inference in integrated computational spectrometry

We propose an inverse-design approach for computational spectrometers in which the scattering media are topology-optimized to achieve better performance in inference of unknown spectra. Unlike traditional end-to-end approaches, our inverse design of the scattering media does not need a training set of spectra, a distribution of detector noise, or an inference algorithm. Our approach allows the selection of the inference algorithm to be decoupled from that of the scatterer. For smooth spectra, we additionally devise a regularized reconstruction algorithm based on Chebyshev interpolation, which yields higher accuracy compared with conventional methods in which the spectra are sampled at equally spaced frequencies or wavelengths with equal weights. Our approaches are numerically demonstrated via inverse design of integrated computational spectrometers and reconstruction of example spectra. The inverse-designed spectrometers exhibit significantly better performance in the presence of noise than their counterparts with random scatterers. Our method provides a useful complement to end-to-end co-design methods.

physics.optics↗

arXiv2025

Time-reversal-symmetry bounds on electromagnetic fields

For linear electromagnetic systems possessing time-reversal symmetry, we present an approach to bound ratios of internal fields excited from different ports, using only the scattering matrix (S matrix), improving upon previous related bounds by Sounas and Al\`u (2017) [Phys. Rev. Lett. 118, 154302 (2017)]. By reciprocity, emitted-wave amplitudes from internal dipole sources are bounded in a similar way. When applied to coupled-resonant systems, our method constrains ratios of resonant coupling/decay coefficients. We also obtain a relation for the relative phase of fields excited from the two ports and the ratio of field intensities in a two-port system. In addition, although lossy systems do not have time-reversal symmetry, we can still approximately bound loss-induced non-unitarity of the S matrix using only the lossless S matrix. We show numerical validations of the near-tightness of our bounds in various scattering systems.

physics.optics↗

arXiv2024

KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep Hashing

Deep hashing has been widely used for large-scale approximate nearest neighbor search due to its storage and search efficiency. However, existing deep hashing methods predominantly rely on abundant training data, leaving the more challenging scenario of low-resource adaptation for deep hashing relatively underexplored. This setting involves adapting pre-trained models to downstream tasks with only an extremely small number of training samples available. Our preliminary benchmarks reveal that current methods suffer significant performance degradation due to the distribution shift caused by limited training samples. To address these challenges, we introduce Class-Calibration LoRA (CLoRA), a novel plug-and-play approach that dynamically constructs low-rank adaptation matrices by leveraging class-level textual knowledge embeddings. CLoRA effectively incorporates prior class knowledge as anchors, enabling parameter-efficient fine-tuning while maintaining the original data distribution. Furthermore, we propose Knowledge-Guided Discrete Optimization (KIDDO), a framework to utilize class knowledge to compensate for the scarcity of visual information and enhance the discriminability of hash codes. Extensive experiments demonstrate that our proposed method, Knowledge- Anchored Low-Resource Adaptation Hashing (KALAHash), significantly boosts retrieval performance and achieves a 4x data efficiency in low-resource scenarios.

cs.CV↗

arXiv2024

AAAR-1.0: Assessing AI's Potential to Assist Research

Numerous studies have assessed the proficiency of AI systems, particularly large language models (LLMs), in facilitating everyday tasks such as email writing, question answering, and creative content generation. However, researchers face unique challenges and opportunities in leveraging LLMs for their own work, such as brainstorming research ideas, designing experiments, and writing or reviewing papers. In this study, we introduce AAAR-1.0, a benchmark dataset designed to evaluate LLM performance in three fundamental, expertise-intensive research tasks: (i) EquationInference, assessing the correctness of equations based on the contextual information in paper submissions; (ii) ExperimentDesign, designing experiments to validate research ideas and solutions; (iii) PaperWeakness, identifying weaknesses in paper submissions; and (iv) REVIEWCRITIQUE, identifying each segment in human reviews is deficient or not. AAAR-1.0 differs from prior benchmarks in two key ways: first, it is explicitly research-oriented, with tasks requiring deep domain expertise; second, it is researcher-oriented, mirroring the primary activities that researchers engage in on a daily basis. An evaluation of both open-source and proprietary LLMs reveals their potential as well as limitations in conducting sophisticated research tasks. We will keep iterating AAAR-1.0 to new versions.

cs.CL↗

arXiv2024

Stratified Avatar Generation from Sparse Observations

Estimating 3D full-body avatars from AR/VR devices is essential for creating immersive experiences in AR/VR applications. This task is challenging due to the limited input from Head Mounted Devices, which capture only sparse observations from the head and hands. Predicting the full-body avatars, particularly the lower body, from these sparse observations presents significant difficulties. In this paper, we are inspired by the inherent property of the kinematic tree defined in the Skinned Multi-Person Linear (SMPL) model, where the upper body and lower body share only one common ancestor node, bringing the potential of decoupled reconstruction. We propose a stratified approach to decouple the conventional full-body avatar reconstruction pipeline into two stages, with the reconstruction of the upper body first and a subsequent reconstruction of the lower body conditioned on the previous stage. To implement this straightforward idea, we leverage the latent diffusion model as a powerful probabilistic generator, and train it to follow the latent distribution of decoupled motions explored by a VQ-VAE encoder-decoder model. Extensive experiments on AMASS mocap dataset demonstrate our state-of-the-art performance in the reconstruction of full-body motions.

cs.CV↗

arXiv2024

GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation

Creating 4D fields of Gaussian Splatting from images or videos is a challenging task due to its under-constrained nature. While the optimization can draw photometric reference from the input videos or be regulated by generative models, directly supervising Gaussian motions remains underexplored. In this paper, we introduce a novel concept, Gaussian flow, which connects the dynamics of 3D Gaussians and pixel velocities between consecutive frames. The Gaussian flow can be efficiently obtained by splatting Gaussian dynamics into the image space. This differentiable process enables direct dynamic supervision from optical flow. Our method significantly benefits 4D dynamic content generation and 4D novel view synthesis with Gaussian Splatting, especially for contents with rich motions that are hard to be handled by existing methods. The common color drifting issue that happens in 4D generation is also resolved with improved Guassian dynamics. Superior visual quality on extensive experiments demonstrates our method's effectiveness. Quantitative and qualitative evaluations show that our method achieves state-of-the-art results on both tasks of 4D generation and 4D novel view synthesis. Project page: https://zerg-overmind.github.io/GaussianFlow.github.io/

cs.CV↗

arXiv2024

Can generative AI and ChatGPT outperform humans on cognitive-demanding problem-solving tasks in science?

This study aimed to examine an assumption that generative artificial intelligence (GAI) tools can overcome the cognitive intensity that humans suffer when solving problems. We compared the performance of ChatGPT and GPT-4 on 2019 NAEP science assessments with students by cognitive demands of the items. Fifty-four tasks were coded by experts using a two-dimensional cognitive load framework, including task cognitive complexity and dimensionality. ChatGPT and GPT-4 responses were scored using the scoring keys of NAEP. The analysis of the available data was based on the average student ability scores for students who answered each item correctly and the percentage of students who responded to individual items. Results showed that both ChatGPT and GPT-4 consistently outperformed most students who answered the NAEP science assessments. As the cognitive demand for NAEP tasks increases, statistically higher average student ability scores are required to correctly address the questions. This pattern was observed for students in grades 4, 8, and 12, respectively. However, ChatGPT and GPT-4 were not statistically sensitive to the increase in cognitive demands of the tasks, except for Grade 4. As the first study focusing on comparing GAI and K-12 students in problem-solving in science, this finding implies the need for changes to educational objectives to prepare students with competence to work with GAI tools in the future. Education ought to emphasize the cultivation of advanced cognitive skills rather than depending solely on tasks that demand cognitive intensity. This approach would foster critical thinking, analytical skills, and the application of knowledge in novel contexts. Findings also suggest the need for innovative assessment practices by moving away from cognitive intensity tasks toward creativity and analytical skills to avoid the negative effects of GAI on testing more efficiently.

cs.AI↗

arXiv2022

Observation of Floquet topological phases with large Chern numbers

One of the most intriguing advantage of Floquet engineering is to generate new phases with large topological invariants. In this work, we experimentally simulate a periodically quenched generalized Haldane model on an NV center in diamond, and observe its Floquet Chern insulator phases with Chern numbers $C=1,2,4$ by imaging the static and dynamic spin textures in momentum space. Our work reveals the power of Floquet driving in transforming system's topology and generating large Chern number phases. It further establishes a unique experimental scheme to detect Floquet topological phases in two and higher spatial dimensions.

quant-ph↗

arXiv2022

HoW-3D: Holistic 3D Wireframe Perception from a Single Image

This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images. As the non-front surfaces of an object cannot be directly observed in a single view, estimating the non-line-of-sight (NLOS) geometries in HoW-3D is a fundamentally challenging problem and remains open in computer vision. We study the problem of HoW-3D by proposing an ABC-HoW benchmark, which is created on top of CAD models sourced from the ABC-dataset with 12k single-view images and the corresponding holistic 3D wireframe models. With our large-scale ABC-HoW benchmark available, we present a novel Deep Spatial Gestalt (DSG) model to learn the visible junctions and line segments as the basis and then infer the NLOS 3D structures from the visible cues by following the Gestalt principles of human vision systems. In our experiments, we demonstrate that our DSG model performs very well in inferring the holistic 3D wireframes from single-view images. Compared with the strong baseline methods, our DSG model outperforms the previous wireframe detectors in detecting the invisible line geometry in single-view images and is even very competitive with prior arts that take high-fidelity PointCloud as inputs on reconstructing 3D wireframes.

cs.CV↗

arXiv2022

Inverse-Designed Meta-Optics with Spectral-Spatial Engineered Response to Mimic Color Perception

Meta-optics have rapidly become a major research field within the optics and photonics community, strongly driven by the seemingly limitless opportunities made possible by controlling optical wavefronts through interaction with arrays of sub-wavelength scatterers. As more and more modalities are explored, the design strategies to achieve desired functionalities become increasingly demanding, necessitating more advanced design techniques. Herein, the inverse-design approach is utilized to create a set of single-layer meta-optics that simultaneously focus light and shape the spectra of focused light without using any filters. Thus, both spatial and spectral properties of the meta-optics are optimized, resulting in spectra that mimic the color matching functions of the CIE 1931 XYZ color space, which links the distributions of wavelengths in light and the color perception of a human eye. Experimental demonstrations of these meta-optics show qualitative agreement with the theoretical predictions and help elucidate the focusing mechanism of these devices.

physics.optics↗

arXiv2021

Beating the Standard Quantum Limit under Ambient Conditions with Solid-State Spins

Precision measurement plays a crucial role in all fields of science. The use of entangled sensors in quantum metrology improves the precision limit from the standard quantum limit (SQL) to the Heisenberg limit (HL). To date, most experiments beating the SQL are performed on the sensors which are well isolated under extreme conditions. However, it has not been realized in solid-state spin systems at ambient conditions, owing to its intrinsic complexity for the preparation and survival of pure and entangled quantum states. Here we show a full interferometer sequence beating the SQL by employing a hybrid multi-spin system, namely the nitrogen-vacancy (NV) defect in diamond. The interferometer sequence starts from a deterministic and joint initialization, undergoes entanglement and disentanglement of multiple spins, and ends up with projective measurement. In particular, the deterministic and joint initialization of NV negative state, NV electron spin, and two nuclear spins is realized at room temperature for the first time. By means of optimal control, non-local gates are implemented with an estimated fidelity above the threshold for fault-tolerant quantum computation. With these techniques combined, we achieve two-spin interference with a phase sensitivity of 1.79 \pm 0.06 dB beyond the SQL and three-spin 2.77 \pm 0.10 dB. Moreover, the deviations from the HL induced by experimental imperfections are completely accountable. The techniques used here are of fundamental importance for quantum sensing and computing, and naturally applicable to other solid-state spin systems.

quant-ph↗

arXiv2021

Three-dimensional entanglement on a silicon chip

Entanglement is a counterintuitive feature of quantum physics that is at the heart of quantum technology. High-dimensional quantum states offer unique advantages in various quantum information tasks. Integrated photonic chips have recently emerged as a leading platform for the generation, manipulation and detection of entangled photons. Here, we report a silicon photonic chip that uses novel interferometric resonance-enhanced photon-pair sources, spectral demultiplexers and high-dimensional reconfigurable circuitries to generate, manipulate and analyse path-entangled three-dimensional qutrit states. By minimizing on-chip electrical and thermal cross-talk, we obtain high-quality quantum interference with visibilities above 96.5% and a maximumly entangled qutrit state with a fidelity of 95.5%. We further explore the fundamental properties of entangled qutrits to test quantum nonlocality and contextuality, and to implement quantum simulations of graphs and high-precision optical phase measurements. Our work paves the path for the development of multiphoton high-dimensional quantum technologies.

quant-ph↗

arXiv2020

Experimental study of quantum coherence decomposition and trade-off relations in a tripartite system

Quantum coherence is the most fundamental of all quantum quantifiers, underlying other well-known quantities such as entanglement, quantum discord, and Bell correlations. It can be distributed in a multipartite system in various ways -- for example, in a bipartite system it can exist within subsystems (local coherence) or collectively between the subsystems (global coherence) and exhibits a trade-off relation. In quantum systems with more than two subsystems, there are more trade-off relations, due to the various decomposition ways of the coherence. In this paper, we experimentally verify these coherence trade-off relations in adiabatically evolved quantum systems using a spin system by changing the state from a product state to a tripartite entangled state. We study the full set of coherence trade-off relations between the original state, the bipartite product state, the tripartite product state, and the decohered product state. We also experimentally verify the monogamy inequality and show that both the quantum systems are polygamous except for the initial product state. We find that despite the different types of states involved, the properties of the state in terms of coherence and monogamy are equivalent. This illustrates the utility of using coherence as a characterization tool for quantum states.

quant-ph↗

arXiv2020

A Simple Phase Retrieval Algorithm from a Single Shot Interferogram

Traditional phase-shifting interferometry technique cannot be used to measure time-varying phase distributions. But single shot techniques could resolve the problem. Many efforts have been made on the phase retrieval methods from a single shot interferogram. In the paper, a simple and effective method is presented without complex computation. The interference fringe is transferred to a phase distribution with a look-up-table. And then it is divided into different regions according to the parity of every pixel. The pixels in the same region have the same parity, which determines the wrapped phase. Additionally, the light spot displacement of a local wavefront is obtained to solve the global sign ambiguity. The theoretical simulation results indicate that the PV of wavefront error is 0.00054(lambda) and the rms is 0.000125(lambda), which is much better than the results from the Fast Fourier Transformation method. We also use it in the experimentally measured interferogram. Our algorithm has the advantages of simplicity, high precision and effective for both open and closed interferometer fringes, which will be valuable for real time monitoring the optical elements shape during their processing.

physics.ins-det↗