arXiv subjects

Jiang Lin

Publications and source records attributed to Jiang Lin.

11 recordsLinked to original sources

arXiv2026

InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors

Video virtual try-on is a highly constrained editing task requiring the precise replacement of a target person's clothing while strictly preserving the original video's spatial structure and temporal dynamics. Existing methods heavily rely on auxiliary handcrafted spatial priors (e.g., masks, poses) for editing control. However, these priors are prone to failure in unconstrained real-world videos and often compress rich visual context into incomplete structural signals. Furthermore, standard reconstruction objectives fail to fully capture try-on-specific human preferences. To address these challenges, we propose InstructVVT, an instruction-driven and reference-guided video virtual try-on framework based on a Diffusion Transformer (DiT) that operates without inference-time spatial priors. Our core insight is to recover fine-grained control directly from the input triplet (source video, reference garment, and instruction) via a dual-level reference conditioning scheme. Specifically, an MLLM infers semantic edit tokens for target disambiguation and structural preservation, while a lightweight conditioning pathway explicitly injects fine-grained visual garment details. Finally, we design a try-on-specific reward and utilize the DiffusionNFT algorithm to align the model with human preferences. Extensive experiments on ViViD-S and TripVVT-Bench demonstrate that InstructVVT outperforms state-of-the-art open-source methods in garment fidelity, structural preservation, and temporal consistency, despite requiring fewer inference-time controls.

cs.CV↗

arXiv2026

SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion

Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or resource-intensive retraining, restricting their flexibility and generalization. To bridge this gap, we present \textit{SimInsert}, a training-free paradigm that efficiently decouples the task into intuitive single-frame editing and semantic motion description. By harnessing the robust generative priors of image-to-video diffusion models, SimInsert propagates edits temporally, strictly preserving background invariance while enabling plausible, text-driven interactions between the inserted object and the dynamic environment. Our approach hinges on non-invasive guidance mechanisms that enforce structural consistency, facilitate seamless boundary fusion, and counteract the fidelity drift that typically accumulates during the denoising trajectory. Extensive quantitative experiments validate our efficacy: SimInsert surpasses state-of-the-art methods with an 18.8\% gain in PSNR, 20.1\% in SSIM, and a 44.1\% decrease in LPIPS, offering a streamlined solution for high-fidelity video editing.

cs.CV↗

arXiv2026

TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On

Due to the scarcity of large-scale in-the-wild triplet data and the improper use of masks, the performance of video virtual try-on models remains limited. In this paper, we first introduce **TripVVT-10K**, the largest and most diverse in-the-wild triplet dataset to date, providing explicit video-level cross-garment supervision that existing video datasets lack. Built upon this resource, we develop **TripVVT**, a Diffusion Transformer-based framework that replaces fragile garment masks with a simple, stable human-mask prior, enabling reliable background preservation while remaining robust to real-world motion, occlusion, and cluttered scenes. To support comprehensive evaluation, we further establish **TripVVT-Bench**, a 100-case benchmark covering diverse garments, complex environments, and multi-person scenarios, with metrics spanning video quality, try-on fidelity, background consistency, and temporal coherence. Compared to state-of-the-art academic and commercial systems, TripVVT achieves superior video quality and garment fidelity while markedly improving generalization to challenging in-the-wild videos. We publicly release the dataset and benchmark, which we believe provide a solid foundation for advancing controllable, realistic, and temporally stable video virtual try-on.

cs.CV↗

arXiv2025

FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction

Controlling the spatial and semantic structure of diffusion-generated images remains a challenge. Existing methods like ControlNet rely on handcrafted condition maps and retraining, limiting flexibility and generalization. Inversion-based approaches offer stronger alignment but incur high inference cost due to dual-path denoising. We present FreeControl, a training-free framework for semantic structural control in diffusion models. Unlike prior methods that extract attention across multiple timesteps, FreeControl performs one-step attention extraction from a single, optimally chosen key timestep and reuses it throughout denoising. This enables efficient structural guidance without inversion or retraining. To further improve quality and stability, we introduce Latent-Condition Decoupling (LCD): a principled separation of the key timestep and the noised latent used in attention extraction. LCD provides finer control over attention quality and eliminates structural artifacts. FreeControl also supports compositional control via reference images assembled from multiple sources - enabling intuitive scene layout design and stronger prompt alignment. FreeControl introduces a new paradigm for test-time control, enabling structurally and semantically aligned, visually coherent generation directly from raw images, with the flexibility for intuitive compositional design and compatibility with modern diffusion models at approximately 5 percent additional cost.

cs.CV↗

arXiv2025

OmniStyle2: Learning to Stylize by Learning to Destylize

This paper introduces a scalable paradigm for supervised style transfer by inverting the problem: instead of learning to stylize directly, we learn to destylize, reducing stylistic elements from artistic images to recover their natural counterparts and thereby producing authentic, pixel-aligned training pairs at scale. To realize this paradigm, we propose DeStylePipe, a progressive, multi-stage destylization framework that begins with global general destylization, advances to category-wise instruction adaptation, and ultimately deploys specialized model adaptation for complex styles that prompt engineering alone cannot handle. Tightly integrated into this pipeline, DestyleCoT-Filter employs Chain-of-Thought reasoning to assess content preservation and style removal at each stage, routing challenging samples forward while discarding persistently low-quality pairs. Built on this framework, we construct DeStyle-350K, a large-scale dataset aligning diverse artistic styles with their underlying content. We further introduce BCS-Bench, a benchmark featuring balanced content generality and style diversity for systematic evaluation. Extensive experiments demonstrate that models trained on DeStyle-350K achieve superior stylization quality, validating destylization as a reliable and scalable supervision paradigm for style transfer.

cs.CV↗

arXiv2025

OmniStyle: Filtering High Quality Style Transfer Data at Scale

In this paper, we introduce OmniStyle-1M, a large-scale paired style transfer dataset comprising over one million content-style-stylized image triplets across 1,000 diverse style categories, each enhanced with textual descriptions and instruction prompts. We show that OmniStyle-1M can not only enable efficient and scalable of style transfer models through supervised training but also facilitate precise control over target stylization. Especially, to ensure the quality of the dataset, we introduce OmniFilter, a comprehensive style transfer quality assessment framework, which filters high-quality triplets based on content preservation, style consistency, and aesthetic appeal. Building upon this foundation, we propose OmniStyle, a framework based on the Diffusion Transformer (DiT) architecture designed for high-quality and efficient style transfer. This framework supports both instruction-guided and image-guided style transfer, generating high resolution outputs with exceptional detail. Extensive qualitative and quantitative evaluations demonstrate OmniStyle's superior performance compared to existing approaches, highlighting its efficiency and versatility. OmniStyle-1M and its accompanying methodologies provide a significant contribution to advancing high-quality style transfer, offering a valuable resource for the research community.

cs.CV↗

arXiv2025

Inversion-Free Video Style Transfer with Trajectory Reset Attention Control and Content-Style Bridging

Video style transfer aims to alter the style of a video while preserving its content. Previous methods often struggle with content leakage and style misalignment, particularly when using image-driven approaches that aim to transfer precise styles. In this work, we introduce Trajectory Reset Attention Control (TRAC), a novel method that allows for high-quality style transfer while preserving content integrity. TRAC operates by resetting the denoising trajectory and enforcing attention control, thus enhancing content consistency while significantly reducing the computational costs against inversion-based methods. Additionally, a concept termed Style Medium is introduced to bridge the gap between content and style, enabling a more precise and harmonious transfer of stylistic elements. Building upon these concepts, we present a tuning-free framework that offers a stable, flexible, and efficient solution for both image and video style transfer. Experimental results demonstrate that our proposed framework accommodates a wide range of stylized outputs, from precise content preservation to the production of visually striking results with vibrant and expressive styles.

cs.CV↗

arXiv2023

A Comprehensive Augmentation Framework for Anomaly Detection

Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of anomaly varies across different classes, potentially leading to a biased training distribution. This paper analyzes crucial traits of simulated anomalies that contribute to the training of reconstructive networks and condenses them into several methods, thus creating a comprehensive framework by selectively utilizing appropriate combinations. Furthermore, we integrate this framework with a reconstruction-based approach and concurrently propose a split training strategy that alleviates the issue of overfitting while avoiding introducing interference to the reconstruction process. The evaluations conducted on the MVTec anomaly detection dataset demonstrate that our method outperforms the previous state-of-the-art approach, particularly in terms of object classes. To evaluate generalizability, we generate a simulated dataset comprising anomalies with diverse characteristics since the original test samples only include specific types of anomalies and may lead to biased evaluations. Experimental results demonstrate that our approach exhibits promising potential for generalizing effectively to various unforeseen anomalies encountered in real-world scenarios.

cs.AI↗

arXiv2023

Exploring the Relationship between Samples and Masks for Robust Defect Localization

Defect detection aims to detect and localize regions out of the normal distribution.Previous approaches model normality and compare it with the input to identify defective regions, potentially limiting their generalizability.This paper proposes a one-stage framework that detects defective patterns directly without the modeling process.This ability is adopted through the joint efforts of three parties: a generative adversarial network (GAN), a newly proposed scaled pattern loss, and a dynamic masked cycle-consistent auxiliary network. Explicit information that could indicate the position of defects is intentionally excluded to avoid learning any direct mapping.Experimental results on the texture class of the challenging MVTec AD dataset show that the proposed method is 2.9% higher than the SOTA methods in F1-Score, while substantially outperforming SOTA methods in generalizability.

cs.CV↗

arXiv2023

Single OR multi-site event discrimination of strip multi-electrode high purity germanium detector via pulse shape analysis method

In order to suppress the background in rare event detection experiments such as 0{\nu}\b{eta}\b{eta}, this paper developed a set of single/multi-site event pulse shape discrimination methods suitable for strip multi-electrode high-purity germanium detectors. In the simulation of 228Th, this method achieves 7.92 times suppression of SEP events at 2103 keV with a 57.43 % survival rate of DEP events at 1592 keV. The experimental study of 57Co and 137Cs sources was carried out by using the self-developed strip multi-electrode high-purity germanium detector prototype measurement system and compared with the simulation results. The results show that the discrimination effect of the PSD method on the experimental waveform is relatively consistent with that of the simulated waveform. The PSD method was used to identify the 0{\nu}\b{eta}\b{eta} background events of 76Ge. The survival rate of 0{\nu}\b{eta}\b{eta} events was 49.16 %, while the main background events 68Ge and 60Co, were 36.23 times and 31.45 times, respectively. The background suppression effects of 232Th and 238U were 4.79 times and 5.06 times, respectively. The results show that the strip multi-electrode high-purity germanium detector can be used for single/multi-site event discrimination and background suppression research. This method is expected to be applied in the measurement of 0{\nu}\b{eta}\b{eta} and other rare events in China Jinping Underground Laboratory in the future.

physics.ins-det↗

arXiv2017

Biaxial compression of centimeter scale graphene on strictly 2D substrate

Biaxial compression of centimetre-scale graphene, freely standing on the surface of water is studied. Within this platform, we report full stress-strain compression of graphene identifying elastic and plastic deformations. The Young's modulus follows a scaling law and falls two orders of magnitude below the commonly reported values with microscale graphene samples. Such results strongly confirm that graphene - in its very natural form - lacks any intrinsic elastic parameters. Different functionalization/manipulation of graphene lattice affects the mechanics of graphene differently; particularly the effect of the sp3 hybridization and crystalline voids on the yield strength of graphene is explored. Crumpling of graphene is accompanied by gradual generation and transformation of wrinkles which brings about viscoelasticity in graphene, observed for the first time in this paper. Additionally, we report a peculiar correlation between the morphology and the distribution of the strain in graphene lattice.

cond-mat.mtrl-sci↗