Author name cluster

Vishal Patel

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

1 author row

YNICL Journal 2026 Journal Article

Enhancing 7T MRI for deep brain stimulation with deep-learning based image reconstruction and dynamic parallel transmission

Justyna O. Ekert
Vishal Patel
Xiangzhi Zhou
Shengzhen Tao
Patrick Liebig
Jürgen Herrler
Thomas Yu
Dominik Nickel

OBJECTIVE: Precise targeting of subcortical structures is crucial for deep brain stimulation (DBS). Although 7T MRI provides superior resolution and contrast, its clinical adoption remains limited by B1+ transmit inhomogeneity, prolonged scan times, and motion sensitivity. This study applied deep learning (DL)-based image reconstruction and dynamic parallel transmission (pTx) to optimize DBS protocols and improve image quality. METHODS: Thirteen patients scanned using a conventional 7T DBS protocol were compared to 13 imaged after implementing DL reconstruction and dynamic pTx. Two readers scored image quality, motion artifact, and target conspicuity on 5-point Likert scales. Ordinal logistic regression was used to calculate odds ratios (OR) for improvements with the enhanced protocol, adjusted for multiple comparisons. RESULTS: Enhanced MP2RAGE reduced voxel volume by 65.8% and scan time by 32.9%, with improved image quality (OR = 4.4;p = 0.003), target conspicuity (OR = 3.4;p = 0.011), and reduced motion artifacts (OR = 3.8;p = 0.006). Fast gray matter acquisition T1 inversion recovery (FGATIR) scan time decreased by 45.2% with improved target delineation of both globus pallidus interna (OR = 22.9;p < 0.001) and dentato-rubro-thalamic tract (OR = 8.8;p < 0.001). T2-weighted sampling perfection with application-optimized contrasts using different flip angle evolutions (SPACE) improved subthalamic nucleus (STN) delineation (OR = 25.3;p < 0.001). Susceptibility-weighted imaging (SWI) improved image quality (OR = 17.4;p < 0.001), STN delineation (OR = 16.9;p < 0.001), and reduced scan time by 42.6%. Enhanced 3D spoiled gradient recall echo improved image quality (OR = 17.4;p < 0.001) and vessel visualization (OR = 26.1;p < 0.001) with reduced motion artifact (OR = 8.8;p < 0.001). Scan time decreased from 4:33 to 1:35, reducing protocol duration from 42:16 to 26:40 (36.9%). CONCLUSIONS: DL reconstruction and dynamic pTx improved image quality, target definition, and motion robustness while shortening 7T DBS protocol time.

Details DOI

NeurIPS Conference 2025 Conference Paper

A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks

Mucong Ding
Bang An
Tahseen Rabbani
Chenghao Deng
Anirudh Satheesh
Souradip Chakraborty
Mehrdad Saberi
Yuxin Wen

AI-generated images have become pervasive, raising critical concerns around content authenticity, intellectual property, and the spread of misinformation. Invisible watermarks offer a promising solution for identifying AI-generated images, preserving content provenance without degrading visual quality. However, their real-world robustness remains uncertain due to the lack of standardized evaluation protocols and large-scale stress testing. To bridge this gap, we organized “Erasing the Invisible, ” a NeurIPS 2024 competition and newly established benchmark designed to systematically stress testing the resilience of watermarking techniques. The competition introduced two attack tracks—Black-box and Beige-box—that simulate practical scenarios with varying levels of attacker knowledge on watermarks, providing a comprehensive assessment of watermark robustness. The competition attracted significant global participation, with 2, 722 submissions from 298 teams. Through a rigorous evaluation pipeline featuring real-time feedback and human-verified final rankings, participants developed and demonstrated new attack strategies that revealed critical vulnerabilities in state-of-the-art watermarking methods. On average, the top-5 teams in both tracks could remove watermarks from $\geq$ 89% of the images while preserving high visual quality, setting strong baselines for future research on watermark attacks and defenses. To support continued progress in this field, we summarize the insights and lessons learned from this competition in this paper, and release the benchmark dataset, evaluation toolkit, and competition results. “Erasing the Invisible” establishes a valuable open resource for advancing more robust watermarking techniques and strengthening content provenance in the era of generative AI.

PDF Details

NeurIPS Conference 2025 Conference Paper

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

Yana Wei
Liang Zhao
Jianjian Sun
Kangheng Lin
jisheng yin
Jingcheng Hu
Yinmin Zhang
En Yu

The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs) to unlock advanced visual reasoning. We introduce a two-stage paradigm built on Qwen2. 5-VL-7B: a massive linguistic cold-start fine-tuning, followed by multimodal reinforcement learning (RL) spanning nearly 1, 000 steps—surpassing all previous open-source efforts in scale. This pioneering work reveals three fundamental insights: 1) Behavior transfer emerges surprisingly early in cold start due to linguistic mental imagery. 2) Cold start broadly memorizes visual behaviors, while RL critically discerns and scales up effective patterns. 3) Transfer strategically favors high-utility behaviors such as visual reflection. Our resulting model, Open-Vision-Reasoner (OVR), achieves state-of-the-art performance on a suite of reasoning benchmarks, including 95. 3% on MATH500, 51. 8% on MathVision and 54. 6% on MathVerse. We release our model, data, and training dynamics to catalyze the development of more capable, behavior-aligned multimodal reasoners.

PDF Details

AAAI Conference 2023 Conference Paper

JR2Net: Joint Monocular 3D Face Reconstruction and Reenactment

Jiaxiang Shang
Yu Zeng
Xin Qiao
Xin Wang
Runze Zhang
Guangyuan Sun
Vishal Patel
Hongbo Fu

Face reenactment and reconstruction benefit various applications in self-media, VR, etc. Recent face reenactment methods use 2D facial landmarks to implicitly retarget facial expressions and poses from driving videos to source images, while they suffer from pose and expression preservation issues for cross-identity scenarios, i.e., when the source and the driving subjects are different. Current self-supervised face reconstruction methods also demonstrate impressive results. However, these methods do not handle large expressions well, since their training data lacks samples of large expressions, and 2D facial attributes are inaccurate on such samples. To mitigate the above problems, we propose to explore the inner connection between the two tasks, i.e., using face reconstruction to provide sufficient 3D information for reenactment, and synthesizing videos paired with captured face model parameters through face reenactment to enhance the expression module of face reconstruction. In particular, we propose a novel cascade framework named JR2Net for Joint Face Reconstruction and Reenactment, which begins with the training of a coarse reconstruction network, followed by a 3D-aware face reenactment network based on the coarse reconstruction results. In the end, we train an expression tracking network based on our synthesized videos composed by image-face model parameter pairs. Such an expression tracking network can further enhance the coarse face reconstruction. Extensive experiments show that our JR2Net outperforms the state-of-the-art methods on several face reconstruction and reenactment benchmarks.

PDF Details DOI

AAAI Conference 2023 Conference Paper

VIDM: Video Implicit Diffusion Models

Kangfu Mei
Vishal Patel

Diffusion models have emerged as a powerful generative method for synthesizing high-quality and diverse set of images. In this paper, we propose a video generation method based on diffusion models, where the effects of motion are modeled in an implicit condition manner, i.e. one can sample plausible video motions according to the latent feature of frames. We improve the quality of the generated videos by proposing multiple strategies such as sampling space truncation, robustness penalty, and positional group normalization. Various experiments are conducted on datasets consisting of videos with different resolutions and different number of frames. Results show that the proposed method outperforms the state-of-the-art generative adversarial network-based methods by a significant margin in terms of FVD scores as well as perceptible visual quality.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Resource-Adaptive Federated Learning with All-In-One Neural Composition

Yiqun Mei
Pengfei Guo
Mo Zhou
Vishal Patel

Conventional Federated Learning (FL) systems inherently assume a uniform processing capacity among clients for deployed models. However, diverse client hardware often leads to varying computation resources in practice. Such system heterogeneity results in an inevitable trade-off between model complexity and data accessibility as a bottleneck. To avoid such a dilemma and achieve resource-adaptive federated learning, we introduce a simple yet effective mechanism, termed All-In-One Neural Composition, to systematically support training complexity-adjustable models with flexible resource adaption. It is able to efficiently construct models at various complexities using one unified neural basis shared among clients, instead of pruning the global model into local ones. The proposed mechanism endows the system with unhindered access to the full range of knowledge scattered across clients and generalizes existing pruning-based solutions by allowing soft and learnable extraction of low footprint models. Extensive experiment results on popular FL benchmarks demonstrate the effectiveness of our approach. The resulting FL system empowered by our All-In-One Neural Composition, called FLANC, manifests consistent performance gains across diverse system/data heterogeneous setups while keeping high efficiency in computation and communication.

PDF Details

NeurIPS Conference 2020 Conference Paper

Deep Subspace Clustering with Data Augmentation

Mahdi Abavisani
Alireza Naghizadeh
Dimitris Metaxas
Vishal Patel

The idea behind data augmentation techniques is based on the fact that slight changes in the percept do not change the brain cognition. In classification, neural networks use this fact by applying transformations to the inputs to learn to predict the same label. However, in deep subspace clustering (DSC), the ground-truth labels are not available, and as a result, one cannot easily use data augmentation techniques. We propose a technique to exploit the benefits of data augmentation in DSC algorithms. We learn representations that have consistent subspaces for slightly transformed inputs. In particular, we introduce a temporal ensembling component to the objective function of DSC algorithms to enable the DSC networks to maintain consistent subspaces for random transformations in the input data. In addition, we provide a simple yet effective unsupervised procedure to find efficient data augmentation policies. An augmentation policy is defined as an image processing transformation with a certain magnitude and probability of being applied to each image in each epoch. We search through the policies in a search space of the most common augmentation policies to find the best policy such that the DSC network yields the highest mean Silhouette coefficient in its clustering results on a target dataset. Our method achieves state-of-the-art performance on four standard subspace clustering datasets.

PDF Details

YNIMG Journal 2010 Journal Article

LONI MiND: Metadata in NIfTI for DWI

Vishal Patel
Ivo D. Dinov
John D. Van Horn
Paul M. Thompson
Arthur W. Toga

A wide range of computational methods have been developed for reconstructing white matter geometry from a set of diffusion-weighted images (DWIs), and many clinical studies rely on publicly-available implementations of these methods for analyzing DWI datasets. Unfortunately, the poor interoperability between DWI analysis tools often effectively restricts users to the algorithms provided by a single software suite, which may be suboptimal relative to those in other packages, or outdated given recent developments in the field. A major barrier to data portability and the interoperability between DWI analysis tools is the lack of a standard format for representing and communicating essential DWI-related metadata at various stages of post-processing. In this report, we address this issue by developing a framework for storing metadata in NIfTI for DWI (MiND). We utilize the standard NIfTI format extension mechanism to store essential DWI metadata in an extended header for multiple commonly-encountered DWI data structures. We demonstrate the utility of this approach by implementing a full suite of tools for DWI analysis workflows which communicate solely through the MiND mechanism. We also show that the MiND framework allows for simple, direct DWI data visualization, and we illustrate its effectiveness by constructing a group atlas for 330 subjects using solely MiND-centric tools for DWI processing. Our results indicate that the MiND framework provides a practical solution to the problem of interoperability between DWI analysis tools, and it effectively expands the analysis options available to end users.

Details DOI

YNIMG Journal 2010 Journal Article

Mesh-based spherical deconvolution: A flexible approach to reconstruction of non-negative fiber orientation distributions

Vishal Patel
Yonggang Shi
Paul M. Thompson
Arthur W. Toga

Diffusion-weighted MRI has enabled the imaging of white matter architecture in vivo. Fiber orientations have classically been assumed to lie along the major eigenvector of the diffusion tensor, but this approach has well-characterized shortcomings in voxels containing multiple fiber populations. Recently proposed methods for recovery of fiber orientation via spherical deconvolution utilize a spherical harmonics framework and are susceptible to noise, yielding physically-invalid results even when additional measures are taken to minimize such artifacts. In this work, we reformulate the spherical deconvolution problem onto a discrete spherical mesh. We demonstrate how this formulation enables the estimation of fiber orientation distributions which strictly satisfy the physical constraints of realness, symmetry, and non-negativity. Moreover, we analyze the influence of the flexible regularization parameters included in our formulation for tuning the smoothness of the resultant fiber orientation distribution (FOD). We show that the method is robust and reliable by reconstructing known crossing fiber anatomy in multiple subjects. Finally, we provide a software tool for computing the FOD using our new formulation in hopes of simplifying and encouraging the adoption of spherical deconvolution techniques.

Details DOI