arXiv subjects

Jingwei Ma

Publications and source records attributed to Jingwei Ma.

13 recordsLinked to original sources

arXiv2026

MicroZoom: Structure-Preserving Detail Synthesis at Extreme Scale

We introduce MicroZoom, a generative framework for gigapixel image synthesis at the microscopic scale. Given a standard photograph and a sparse set of consumer-grade microscope close-ups, MicroZoom synthesizes a seamless, gigapixel-resolution image grounded in the material character of the real references, enabling exploratory visualization of microscopic texture across the full spatial extent of an object. Our goal is plausible synthesis, not exact reconstruction. We focus on full-image, reference-based, extreme-scale super-resolution at magnification levels of up to 350x, a setting that introduces two major challenges: (1) recovering texture-specific detail from highly lossy inputs near ambiguous material boundaries, and (2) preserving correct large-scale pattern structure, such as the repeating geometry of a fabric weave, across millions of local predictions. We address these with a two-stage cascaded design, where the first stage recovers global pattern coherence and the second refines local texture detail, supplemented by a segmentation mask to guide synthesis at ambiguous boundaries. We verify our approach on a collection of self-captured everyday objects and demonstrate globally coherent, materially grounded gigapixel imagery.

cs.CV↗

arXiv2026

GarmentZoom: Generating Zoomable Images from Garment Listings

Online product listings for garments often include an overview photo and a close-up to show garment details. However, each photo focuses on either field of view or garment detail, forcing users to alternate between views and breaking browsing continuity. We present GarmentZoom, a system that enhances the full-view photo to match the fidelity of its accompanying close-up, enabling seamless zoom-and-pan exploration. Unlike standard reference-based super-resolution, our setting involves close-up references that are spatially unaligned with the full view, and scale factors that vary substantially across garments 3-20$\times$. Prior work typically relies on alignment to transfer details or requires per-instance fine-tuning to memorize them. Instead, we train a single model that supports a continuous range of scales across diverse garments. Our approach synthesizes details without requiring spatial alignment and matches the quality of per-instance methods with a fraction of the training cost.

cs.CV↗

arXiv2026

CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation

Vision-Language Models (VLMs) have shown remarkable progress in Vision-Language Navigation (VLN), offering new possibilities for navigation decision-making that could benefit both robotic platforms and human users. However, real-world navigation is inherently conditioned by the agent's mobility constraints. For example, a sweeping robot cannot traverse stairs, while a quadruped can. We introduce Capability-Conditioned Navigation (CapNav), a benchmark designed to evaluate how well VLMs can navigate complex indoor spaces given an agent's specific physical and operational capabilities. CapNav defines five representative human and robot agents, each described with physical dimensions, mobility capabilities, and environmental interaction abilities. CapNav provides 45 real-world indoor scenes, 473 navigation tasks, and 2365 QA pairs to test if VLMs can traverse indoor environments based on agent capabilities. We evaluate 13 modern VLMs and find that current VLM's navigation performance drops sharply as mobility constraints tighten, and that even state-of-the-art models struggle with obstacle types that require reasoning on spatial dimensions. We conclude by discussing the implications for capability-aware navigation and the opportunities for advancing embodied spatial reasoning in future VLMs. The benchmark is available at https://github.com/makeabilitylab/CapNav

cs.CV↗

arXiv2025

FlyMeThrough: Human-AI Collaborative 3D Indoor Mapping with Commodity Drones

Indoor mapping data is crucial for routing, navigation, and building management, yet such data are widely lacking due to the manual labor and expense of data collection, especially for larger indoor spaces. Leveraging recent advancements in commodity drones and photogrammetry, we introduce FlyMeThrough -- a drone-based indoor scanning system that efficiently produces 3D reconstructions of indoor spaces with human-AI collaborative annotations for key indoor points-of-interest (POI) such as entrances, restrooms, stairs, and elevators. We evaluated FlyMeThrough in 12 indoor spaces with varying sizes and functionality. To investigate use cases and solicit feedback from target stakeholders, we also conducted a qualitative user study with five building managers and five occupants. Our findings indicate that FlyMeThrough can efficiently and precisely create indoor 3D maps for strategic space planning, resource management, and navigation.

cs.HC↗

arXiv2025

UltraZoom: Generating Gigapixel Images from Regular Photos

We present UltraZoom, a system for generating gigapixel-resolution images of objects from casually captured inputs, such as handheld phone photos. Given a full-shot image (global, low-detail) and one or more close-ups (local, high-detail), UltraZoom upscales the full image to match the fine detail and scale of the close-up examples. To achieve this, we construct a per-instance paired dataset from the close-ups and adapt a pretrained generative model to learn object-specific low-to-high resolution mappings. At inference, we apply the model in a sliding window fashion over the full image. Constructing these pairs is non-trivial: it requires registering the close-ups within the full image for scale estimation and degradation alignment. We introduce a simple, robust method for getting registration on arbitrary materials in casual, in-the-wild captures. Together, these components form a system that enables seamless pan and zoom across the entire object, producing consistent, photorealistic gigapixel imagery from minimal input.

cs.CV↗

arXiv2024

VidPanos: Generative Panoramic Videos from Casual Panning Videos

Panoramic image stitching provides a unified, wide-angle view of a scene that extends beyond the camera's field of view. Stitching frames of a panning video into a panoramic photograph is a well-understood problem for stationary scenes, but when objects are moving, a still panorama cannot capture the scene. We present a method for synthesizing a panoramic video from a casually-captured panning video, as if the original video were captured with a wide-angle camera. We pose panorama synthesis as a space-time outpainting problem, where we aim to create a full panoramic video of the same length as the input video. Consistent completion of the space-time volume requires a powerful, realistic prior over video content and motion, for which we adapt generative video models. Existing generative models do not, however, immediately extend to panorama completion, as we show. We instead apply video generation as a component of our panorama synthesis system, and demonstrate how to exploit the strengths of the models while minimizing their limitations. Our system can create video panoramas for a range of in-the-wild scenes including people, vehicles, and flowing water, as well as stationary background features.

cs.CV↗

arXiv2022

Totems: Physical Objects for Verifying Visual Integrity

We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene. Totems bend and redirect light rays, thus providing multiple, albeit distorted, views of the scene within a single image. A defender can use these distorted totem pixels to detect if an image has been manipulated. Our approach unscrambles the light rays passing through the totems by estimating their positions in the scene and using their known geometric and material properties. To verify a totem-protected image, we detect inconsistencies between the scene reconstructed from totem viewpoints and the scene's appearance from the camera viewpoint. Such an approach makes the adversarial manipulation task more difficult, as the adversary must modify both the totem and image pixels in a geometrically consistent manner without knowing the physical properties of the totem. Unlike prior learning-based approaches, our method does not require training on datasets of specific manipulations, and instead uses physical properties of the scene and camera to solve the forensics problem.

cs.CV↗

arXiv2022

Fluctuation analysis for particle-based stochastic reaction-diffusion models

Recent works have derived and proven the large-population mean-field limit for several classes of particle-based stochastic reaction-diffusion (PBSRD) models. These limits correspond to systems of partial integral-differential equations (PIDEs) that generalize standard mass-action reaction-diffusion PDE models. In this work we derive and prove the next order fluctuation corrections to such limits, which we show satisfy systems of stochastic PIDEs with Gaussian noise. Numerical examples are presented to illustrate how including the fluctuation corrections can enable the accurate estimation of higher order statistics of the underlying PBSRD model.

math.PR↗

arXiv2021

Mean Field Limits of Particle-Based Stochastic Reaction-Diffusion Models

Particle-based stochastic reaction-diffusion (PBSRD) models are a popular approach for studying biological systems involving both noise in the reaction process and diffusive transport. In this work we derive coarse-grained deterministic partial integro-differential equation (PIDE) models that provide a mean field approximation to the volume reactivity PBSRD model, a model commonly used for studying cellular processes. We formulate a weak measure-valued stochastic process (MVSP) representation for the volume reactivity PBSRD model, demonstrating for a simplified but representative system that it is consistent with the commonly used Doi Fock Space representation of the corresponding forward equation. We then prove the convergence of the general volume reactivity model MVSP to the mean field PIDEs in the large-population (i.e. thermodynamic) limit.

math.PR↗

arXiv2021

How reaction-diffusion PDEs approximate the large-population limit of stochastic particle models

Reaction-diffusion PDEs and particle-based stochastic reaction-diffusion (PBSRD) models are commonly-used approaches for modeling the spatial dynamics of chemical and biological systems. Standard reaction-diffusion PDE models ignore the underlying stochasticity of spatial transport and reactions, and are often described as appropriate in regimes where there are large numbers of particles in a system. Recent studies have proven the rigorous large-population limit of PBSRD models, showing the resulting mean-field models (MFM) correspond to non-local systems of partial-integro differential equations. In this work we explore the rigorous relationship between standard reaction-diffusion PDE models and the derived MFM. We prove that the former can be interpreted as an asymptotic approximation to the later in the limit that bimolecular reaction kernels are short-range and averaging. As the reactive interaction length scale approaches zero, we prove the MFMs converge at second order to standard reaction-diffusion PDE models. In proving this result we also establish local well-posedness of the MFM model in time for general systems, and global well-posedness for specific reaction systems and kernels. Finally, we illustrate the agreement and disagreement between the MFM, SM and the underlying particle model for several numerical examples.

math.AP↗

arXiv2020

A Unified Model for Recommendation with Selective Neighborhood Modeling

Neighborhood-based recommenders are a major class of Collaborative Filtering (CF) models. The intuition is to exploit neighbors with similar preferences for bridging unseen user-item pairs and alleviating data sparseness. Many existing works propose neural attention networks to aggregate neighbors and place higher weights on specific subsets of users for recommendation. However, the neighborhood information is not necessarily always informative, and the noises in the neighborhood can negatively affect the model performance. To address this issue, we propose a novel neighborhood-based recommender, where a hybrid gated network is designed to automatically separate similar neighbors from dissimilar (noisy) ones, and aggregate those similar neighbors to comprise neighborhood representations. The confidence in the neighborhood is also addressed by putting higher weights on the neighborhood representations if we are confident with the neighborhood information, and vice versa. In addition, a user-neighbor component is proposed to explicitly regularize user-neighbor proximity in the latent space. These two components are combined into a unified model to complement each other for the recommendation task. Extensive experiments on three publicly available datasets show that the proposed model consistently outperforms state-of-the-art neighborhood-based recommenders. We also study different variants of the proposed model to justify the underlying intuition of the proposed hybrid gated network and user-neighbor modeling components.

cs.IR↗

arXiv2020

Hierarchical Text Interaction for Rating Prediction

Traditional recommender systems encounter several challenges such as data sparsity and unexplained recommendation. To address these challenges, many works propose to exploit semantic information from review data. However, these methods have two major limitations in terms of the way to model textual features and capture textual interaction. For textual modeling, they simply concatenate all the reviews of a user/item into a single review. However, feature extraction at word/phrase level can violate the meaning of the original reviews. As for textual interaction, they defer the interactions to the prediction layer, making them fail to capture complex correlations between users and items. To address those limitations, we propose a novel Hierarchical Text Interaction model(HTI) for rating prediction. In HTI, we propose to model low-level word semantics and high-level review representations hierarchically. The hierarchy allows us to exploit textual features at different granularities. To further capture complex user-item interactions, we propose to exploit semantic correlations between each user-item pair at different hierarchies. At word level, we propose an attention mechanism specialized to each user-item pair, and capture the important words for representing each review. At review level, we mutually propagate textual features between the user and item, and capture the informative reviews. The aggregated review representations are integrated into a collaborative filtering framework for rating prediction. Experiments on five real-world datasets demonstrate that HTI outperforms state-of-the-art models by a large margin. Further case studies provide a deep insight into HTI's ability to capture semantic correlations at different levels of granularities for rating prediction.

cs.IR↗

arXiv2019

DBRec: Dual-Bridging Recommendation via Discovering Latent Groups

In recommender systems, the user-item interaction data is usually sparse and not sufficient for learning comprehensive user/item representations for recommendation. To address this problem, we propose a novel dual-bridging recommendation model (DBRec). DBRec performs latent user/item group discovery simultaneously with collaborative filtering, and interacts group information with users/items for bridging similar users/items. Therefore, a user's preference over an unobserved item, in DBRec, can be bridged by the users within the same group who have rated the item, or the user-rated items that share the same group with the unobserved item. In addition, we propose to jointly learn user-user group (item-item group) hierarchies, so that we can effectively discover latent groups and learn compact user/item representations. We jointly integrate collaborative filtering, latent group discovering and hierarchical modelling into a unified framework, so that all the model parameters can be learned toward the optimization of the objective function. We validate the effectiveness of the proposed model with two real datasets, and demonstrate its advantage over the state-of-the-art recommendation models with extensive experiments.

cs.IR↗