arXiv subjects

Stanley H. Chan

Publications and source records attributed to Stanley H. Chan.

At least 19 recordsLinked to original sources

arXiv2026

Restore What Matters: Lessons from Joint Restoration and Recognition

Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom translates to improved recognition. We propose a Joint Restoration-for-Recognition (JR$^2$) paradigm: restore only what downstream tasks truly require, with task signals dictating where, how much, and whether restoration is necessary. JR$^2$ rests on three pillars: (i) Physics, employing optics-accurate turbulence simulation, extensible to blur and noise, to ground restoration in real image formation; (ii) Neuroscience, drawing on selective attention and neuroplasticity to direct model capacity toward identity-critical regions and frames while bypassing already-clean inputs; and (iii) Vision & Learning, coupling recognition loss end-to-end through restoration and alignment so that low-level edits maximize high-level identity stability. Evaluations on IARPA-BRIAR show consistent improvements (e.g., TAR@0.01% FAR +0.6; FNIR@1% FPIR -2.5), while a quality gate skips ~70% of clean frames, reducing cost. Ablations confirm physics priors enhance realism, joint training prevents catastrophic forgetting, and selective restoration suffices in many cases. We conclude that better-looking images are neither necessary nor sufficient; restoration modules must be task-driven, selective, and physically aware. Code, pretrained models, and recipes are provided for integration.

cs.CV↗

arXiv2026

Geometric and Quantum Kernel Methods for Predicting Skeletal Muscle Outcomes in chronic obstructive pulmonary disease

Chronic obstructive pulmonary disease (COPD) affects hundreds of millions of people worldwide, and skeletal-muscle dysfunction is clinically important. Quantum machine learning is increasingly explored for biomedical prediction, but its value in small biomarker cohorts requires benchmarking against strong classical baselines. We analysed a cigarette-smoke COPD cohort of 213 animals with blood and bronchoalveolar-lavage biomarkers to predict tibialis anterior muscle weight, muscle quality, and force. We developed a kernel-geometric quantum hybrid method in which synthetic symmetric positive definite (SPD) references are mapped through a reproducing kernel Hilbert space, compressed using train-only random projection, normalised, and supplied to low-dimensional quantum regression circuits. We benchmarked this approach against classical ridge/kernel models, SPD relational representations, and quantum-kernel regression (QKR). All methods were evaluated using condition-stratified repeated cross-validation. The largest numerical improvement was observed for muscle weight, where the proposed method had the numerically lowest mean root mean squared error (RMSE), approximately 1.8% below the best classical comparator; paired fold-level testing did not establish statistically significant superiority after Holm adjustment, but the endpoint is biologically meaningful. The method also had the numerically lowest mean RMSE for muscle quality. For force, biomarker-only Ridge performed best, suggesting a more linear endpoint structure.

cs.LG↗

arXiv2026

OptiWorld: Optimal Control for Video World Generation under Physical Constraints

Video generation models are becoming a scalable form of world models, but they mainly generate plausible motion rather than proactively control or optimize the underlying dynamics. As a result, an object in the generated video may follow trajectories that are unsafe, not smooth, inefficient, or physically inconsistent. In this work, we propose \textbf{OptiWorld}, a framework that brings classical optimal control into video generation at inference time. OptiWorld first extracts a compact, task-relevant world state, then plans an optimal trajectory under physical constraints, and finally renders the video conditioned on this trajectory. We formulate planning as a geometric problem on a continuous manifold, which converts 3D geometry and task-dependent physical constraints into a unified planning geometry. By adding this optimal-control layer, OptiWorld generates videos with preferable dynamics, demonstrating strong potential in multiple tasks including goal-conditioned image-to-video generation, video dynamics editing, and counterfactual generation.

cs.CV↗

arXiv2026

MetaTele: Compact Refractive Metasurface Computational Telephoto Camera

Smartphone cameras face fundamental form-factor constraints that limit their optical magnification, primarily due to the difficulty of reducing a lens assembly's telephoto ratio, the ratio between total track length (TTL) and effective focal length (EFL). Currently, conventional refractive optics struggle to achieve a telephoto ratio below 0.5 without requiring multiple bulky elements to correct optical aberrations. In this paper, we introduce MetaTele, a novel optics-algorithm co-design that breaks this bottleneck. MetaTele explicitly decouples the acquisition of scene structure and color information. First, it utilizes a compact refractive-metasurface optical assembly to capture a fine-detail structure image under a narrow wavelength band, inherently avoiding severe chromatic aberrations. Second, it captures a broadband color cue using the same optics; although this cue is heavily corrupted by chromatic aberrations, it retains sufficient spectral information to guide post-processing. We then employ a custom one-step diffusion model to computationally fuse these two raw measurements, successfully colorizing the structure image while correcting for system aberrations. We demonstrate a MetaTele prototype, achieving an unprecedented telephoto ratio of 0.44 with a TTL of just 13 mm for RGB imaging, paving the way for DSLR-level telephoto capabilities within smartphone form factors.

eess.IV↗

arXiv2026

FlowSteer: Conditioning Flow Field for Consistent Image Restoration

Flow-based text-to-image (T2I) models excel at prompt-driven image generation, but falter on Image Restoration (IR), often "drifting away" from being faithful to the measurement. Prior work mitigate this drift with data-specific flows or task-specific adapters that are computationally heavy and not scalable across tasks. This raises the question "Can't we efficiently manipulate the existing generative capabilities of a flow model?" To this end, we introduce FlowSteer (FS), an operator-aware conditioning scheme that injects measurement priors along the sampling path,coupling a frozed flow's implicit guidance with explicit measurement constraints. Across super-resolution, deblurring, denoising, and colorization, FS improves measurement consistency and identity preservation in a strictly zero-shot setting-no retrained models, no adapters. We show how the nature of flow models and their sensitivities to noise inform the design of such a scheduler. FlowSteer, although simple, achieves a higher fidelity of reconstructed images, while leveraging the rich generative priors of flow models. All data and code will be publicly available \href{https://tharindu-nirmal.github.io/FlowSteer/}{in this link}.

eess.IV↗

arXiv2026

Pupil Design for Computational Wavefront Estimation

Establishing a precise connection between imaged intensity and the incident wavefront is essential for emerging applications in adaptive optics, holography, computational microscopy, and non-line-of-sight imaging. While prior work has shown that breaking symmetries in pupil design enables wavefront recovery from a single intensity measurement, there is little guidance on how to design a pupil that improves wavefront estimation. In this work we introduce a quantitative asymmetry metric to bridge this gap and, through an extensive empirical study and supporting analysis, demonstrate that increasing asymmetry enhances wavefront recoverability. We analyze the trade-offs in pupil design, and the impact on light throughput along with performance in noise. Both large-scale simulations and optical bench experiments are carried out to support our findings.

eess.IV↗

arXiv2026

NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics

A primary bottleneck in large-scale text-to-video generation today is physical consistency and controllability. Despite recent advances, state-of-the-art models often produce unrealistic motions, such as objects falling upward, or abrupt changes in velocity and direction. Moreover, these models lack precise parameter control, struggling to generate physically consistent dynamics under different initial conditions. We argue that this fundamental limitation stems from current models learning motion distributions solely from appearance, while lacking an understanding of the underlying dynamics. In this work, we propose NewtonGen, a framework that integrates data-driven synthesis with learnable physical principles. At its core lies trainable Neural Newtonian Dynamics (NND), which can model and predict a variety of Newtonian motions, thereby injecting latent dynamical constraints into the video generation process. By jointly leveraging data priors and dynamical guidance, NewtonGen enables physically consistent video synthesis with precise parameter control. All data and code are available at https://github.com/pandayuanyu/NewtonGen

cs.CV↗

arXiv2026

SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation

Images and videos are discrete 2D projections of the 4D world (3D space + time). Most visual understanding, prediction, and generation operate directly on 2D observations, leading to suboptimal performance. We propose SeeU, a novel approach that learns the continuous 4D dynamics and generate the unseen visual contents. The principle behind SeeU is a new 2D$\to$4D$\to$2D learning framework. SeeU first reconstructs the 4D world from sparse and monocular 2D frames (2D$\to$4D). It then learns the continuous 4D dynamics on a low-rank representation and physical constraints (discrete 4D$\to$continuous 4D). Finally, SeeU rolls the world forward in time, re-projects it back to 2D at sampled times and viewpoints, and generates unseen regions based on spatial-temporal context awareness (4D$\to$2D). By modeling dynamics in 4D, SeeU achieves continuous and physically-consistent novel visual generation, demonstrating strong potentials in multiple tasks including unseen temporal generation, unseen spatial generation, and video editing. All data and code will be public at https://yuyuanspace.com/SeeU/

cs.CV↗

arXiv2026

Direct Kernel Optimization: Efficient Design for Opto-Electronic Convolutional Neural Networks

Hybrid opto-electronic neural networks combine optical front-ends with electronic back-ends to perform vision tasks, but joint end-to-end (E2E) optimization of optical and electronic components is computationally expensive due to large parameter spaces and repeated optical convolutions. We propose Direct Kernel Optimization (DKO), a two-stage training framework that first trains a conventional electronic CNN and then synthesizes optical kernels to replicate the first-layer convolutional filters, reducing optimization dimensionality and avoiding hefty simulated optical convolutions during optimization. We evaluate DKO in simulation on a monocular depth estimation model and show that it achieves twice the accuracy of E2E training under equal computational budgets while reducing training time. Given the substantial computational challenges of optimizing hybrid opto-electronic systems, our results position DKO as a scalable optimization approach to train and realize these systems.

eess.IV↗

arXiv2025

Markov-Renewal Single-Photon LiDAR Simulator

Single-photon LiDAR (SP-LiDAR) simulators face a dilemma: fast but inaccurate Poisson models or accurate but prohibitively slow sequential models. This paper breaks that compromise. We present a simulator that achieves both fidelity and speed by focusing on the critical, yet overlooked, component of simulation: the photon count statistics. Our key contribution is a Markov-renewal process (MRP) formulation that, for the first time, analytically predicts the mean and variance of registered photon counts under dead time. To make this MRP model computationally tractable, we introduce a spectral truncation rule that efficiently computes the complex covariance statistics. By proving the shift-invariance of the process, we extend this per-pixel model to full histogram cube generation via a precomputed lookup table. Our method generates 3D cubes indistinguishable from the sequential gold-standard, yet is orders of magnitude faster. This finally enables large-scale, physically-faithful data generation for learning-based SP-LiDAR reconstruction.

eess.SP↗

arXiv2025

Diffusion Algorithm for Metalens Optical Aberration Correction

Metalenses offer a path toward creating ultra-thin optical systems, but they inherently suffer from severe, spatially varying optical aberrations, especially chromatic aberration, which makes image reconstruction a significant challenge. This paper presents a novel algorithmic solution to this problem, designed to reconstruct a sharp, full-color image from two inputs: a sharp, bandpass-filtered grayscale ``structure image'' and a heavily distorted ``color cue'' image, both captured by the metalens system. Our method utilizes a dual-branch diffusion model, built upon a pre-trained Stable Diffusion XL framework, to fuse information from the two inputs. We demonstrate through quantitative and qualitative comparisons that our approach significantly outperforms existing deblurring and pansharpening methods, effectively restoring high-frequency details while accurately colorizing the image.

eess.IV↗

arXiv2025

Real-Time Markov Modeling for Single-Photon LiDAR: $1000 \times$ Acceleration and Convergence Analysis

Asynchronous single-photon LiDAR (SP-LiDAR) is an important imaging modality for high-quality 3D applications and navigation, but the modeling of the timestamp distributions of a SP-LiDAR in the presence of dead time remains a very challenging open problem. Prior works have shown that timestamps form a discrete-time Markov chain, whose stationary distribution can be computed as the leading left eigenvector of a large transition matrix. However, constructing this matrix is known to be computationally expensive because of the coupling between states and the dead time. This paper presents the first non-sequential Markov modeling for the timestamp distribution. The key innovation is an equivalent formulation that reparameterizes the integral bounds and separates the effect of dead time as a deterministic row permutation of a base matrix. This decoupling enables efficient vectorized matrix construction, yielding up to $1000 \times$ acceleration over existing methods. The new model produces a nearly exact stationary distribution when compared with the gold standard Monte Carlo simulations, yet using a fraction of the time. In addition, a new theoretical analysis reveals the impact of the magnitude and phase of the second-largest eigenvalue, which are overlooked in the literature but are critical to the convergence.

eess.SP↗

arXiv2025

Quanta Diffusion

We present Quanta Diffusion (QuDi), a powerful generative video reconstruction method for single-photon imaging. QuDi is an algorithm supporting the latest Quanta Image Sensors (QIS) and Single Photon Avalanche Diodes (SPADs) for extremely low-light imaging conditions. Compared to existing methods, QuDi overcomes the difficulties of simultaneously managing the motion and the strong shot noise. The core innovation of QuDi is to inject a physics-based forward model into the diffusion algorithm, while keeping the motion estimation in the loop. QuDi demonstrates an average of 2.4 dB PSNR improvement over the best existing methods.

eess.IV↗

arXiv2025

Joint Depth and Reflectivity Estimation using Single-Photon LiDAR

Single-Photon Light Detection and Ranging (SP-LiDAR is emerging as a leading technology for long-range, high-precision 3D vision tasks. In SP-LiDAR, timestamps encode two complementary pieces of information: pulse travel time (depth) and the number of photons reflected by the object (reflectivity). Existing SP-LiDAR reconstruction methods typically recover depth and reflectivity separately or sequentially use one modality to estimate the other. Moreover, the conventional 3D histogram construction is effective mainly for slow-moving or stationary scenes. In dynamic scenes, however, it is more efficient and effective to directly process the timestamps. In this paper, we introduce an estimation method to simultaneously recover both depth and reflectivity in fast-moving scenes. We offer two contributions: (1) A theoretical analysis demonstrating the mutual correlation between depth and reflectivity and the conditions under which joint estimation becomes beneficial. (2) A novel reconstruction method, "SPLiDER", which exploits the shared information to enhance signal recovery. On both synthetic and real SP-LiDAR data, our method outperforms existing approaches, achieving superior joint reconstruction quality.

cs.CV↗

arXiv2025

Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation

Atmospheric turbulence is a major source of image degradation in long-range imaging systems. Although numerous deep learning-based turbulence mitigation (TM) methods have been proposed, many are slow, memory-hungry, and do not generalize well. In the spatial domain, methods based on convolutional operators have a limited receptive field, so they cannot handle a large spatial dependency required by turbulence. In the temporal domain, methods relying on self-attention can, in theory, leverage the lucky effects of turbulence, but their quadratic complexity makes it difficult to scale to many frames. Traditional recurrent aggregation methods face parallelization challenges. In this paper, we present a new TM method based on two concepts: (1) A turbulence mitigation network based on the Selective State Space Model (MambaTM). MambaTM provides a global receptive field in each layer across spatial and temporal dimensions while maintaining linear computational complexity. (2) Learned Latent Phase Distortion (LPD). LPD guides the state space model. Unlike classical Zernike-based representations of phase distortion, the new LPD map uniquely captures the actual effects of turbulence, significantly improving the model's capability to estimate degradation by reducing the ill-posedness. Our proposed method exceeds current state-of-the-art networks on various synthetic and real-world TM benchmarks with significantly faster inference speed.

cs.CV↗

arXiv2025

Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait

We address the problem of whole-body person recognition in unconstrained environments. This problem arises in surveillance scenarios such as those in the IARPA Biometric Recognition and Identification at Altitude and Range (BRIAR) program, where biometric data is captured at long standoff distances, elevated viewing angles, and under adverse atmospheric conditions (e.g., turbulence and high wind velocity). To this end, we propose FarSight, a unified end-to-end system for person recognition that integrates complementary biometric cues across face, gait, and body shape modalities. FarSight incorporates novel algorithms across four core modules: multi-subject detection and tracking, recognition-aware video restoration, modality-specific biometric feature encoding, and quality-guided multi-modal fusion. These components are designed to work cohesively under degraded image conditions, large pose and scale variations, and cross-domain gaps. Extensive experiments on the BRIAR dataset, one of the most comprehensive benchmarks for long-range, multi-modal biometric recognition, demonstrate the effectiveness of FarSight. Compared to our preliminary system, this system achieves a 34.1% absolute gain in 1:1 verification accuracy (TAR@0.1% FAR), a 17.8% increase in closed-set identification (Rank-20), and a 34.3% reduction in open-set identification errors (FNIR@1% FPIR). Furthermore, FarSight was evaluated in the 2025 NIST RTE Face in Video Evaluation (FIVE), which conducts standardized face recognition testing on the BRIAR dataset. These results establish FarSight as a state-of-the-art solution for operational biometric recognition in challenging real-world conditions.

cs.CV↗

arXiv2025

Wavefront Estimation From a Single Measurement: Uniqueness and Algorithms

Wavefront estimation is an essential component of adaptive optics where the goal is to recover the underlying phase from its Fourier magnitude. While this may sound identical to classical phase retrieval, wavefront estimation faces more strict requirements regarding uniqueness as adaptive optics systems need a unique phase to compensate for the distorted wavefront. Existing real-time wavefront estimation methodologies are dominated by sensing via specialized optical hardware due to their high speed, but they often have a low spatial resolution. A computational method that can perform both fast and accurate wavefront estimation with a single measurement can improve resolution and bring new applications such as real-time passive wavefront estimation, opening the door to a new generation of medical and defense applications. In this paper, we tackle the wavefront estimation problem by observing that the non-uniqueness is related to the geometry of the pupil shape. By analyzing the source of ambiguities and breaking the symmetry, we present a joint optics-algorithm approach by co-designing the shape of the pupil and the reconstruction neural network. Using our proposed lightweight neural network, we demonstrate wavefront estimation of a phase of size $128\times 128$ at $5,200$ frames per second on a CPU computer, achieving an average Strehl ratio up to $0.98$ in the noiseless case. We additionally test our method on real measurements using a spatial light modulator. Code is available at https://pages.github.itap.purdue.edu/StanleyChanGroup/wavefront-estimation/.

eess.SP↗

arXiv2025

Tutorial on Diffusion Models for Imaging and Vision

The astonishing growth of generative tools in recent years has empowered many exciting applications in text-to-image generation and text-to-video generation. The underlying principle behind these generative tools is the concept of diffusion, a particular sampling mechanism that has overcome some shortcomings that were deemed difficult in the previous approaches. The goal of this tutorial is to discuss the essential ideas underlying the diffusion models. The target audience of this tutorial includes undergraduate and graduate students who are interested in doing research on diffusion models or applying these models to solve other problems.

cs.LG↗