arXiv subjects

Bolei Xu

Publications and source records attributed to Bolei Xu.

10 recordsLinked to original sources

arXiv2026

DualCast: Dual-Image Conditioned Diffusion Transformers for Digital Human E-Commerce Video Generation

Digital human e-commerce video generation requires preserving product appearance, human identity, and overall video style during dynamic demonstrations. Although recent models support multiple reference images, their general conditioning schemes do not explicitly distinguish the asymmetric roles of "what is presented" and "who presents it." Consequently, generated videos may favor a single reference, resulting in product distortion, identity drift, or single-reference collapse. To address this issue, we propose DualCast, a role-addressed dual-image conditioning framework for video generation. By explicitly modeling the distinct roles of product and human conditions, DualCast reduces role ambiguity and feature competition between references. First, a dual-spatiotemporal slot injection mechanism VAE-encodes the product and human images separately and places their latent features at the front and rear boundaries of the DiT sequence, enabling sequence-level condition separation and directed injection. Second, a mask-guided region-weighted loss strengthens supervision over product, face, and product-face overlap regions, improving generation fidelity in critical areas. Third, image condition dropout enables a single model to support dual-image, product-only, and human-only generation. In addition, we construct a curated dataset of 10K e-commerce videos for model training. Experimental results demonstrate the strong performance of DualCast.

cs.CV↗

arXiv2026

CrossPair: Unlocking Generalist Visual Transformation Learning in Image Editors

Language models switch tasks from demonstrations, but vision still often relies on separate systems for restoration, editing, and stylization. A before--after example offers a shared instruction only if the transferable change can be separated from the scene that demonstrates it. We introduce CrossPair, which adapts a pretrained multimodal image editor to transfer diverse transformations from one exemplar pair. Exemplar-before, exemplar-after, and query images take fixed roles in its native VLM and VAE pathways: the VLM extracts operation semantics, while the VAE retains fine appearance and structure. A training-only, change-aware DINOv3 objective aligns feature-change directions across content-distinct scenes, guiding the output to follow the demonstrated relation without an inference-time encoder. We construct Transform-360K by grouping filtered pairs from conditional representations, restoration, editing, virtual try-on, and stylization under shared transformations. On Relation252K-derived seen and held-out transformations, \method improves target agreement and edit-direction similarity over released systems. Ablations show that the semantic and visual exemplar routes are complementary and that DINO relation alignment further strengthens transfer; Transform-360K training also improves aggregate held-out-operation scores.

cs.CV↗

arXiv2026

One Evaluation Is Enough: Inversion-Free Image Editing with Trajectory Correction

Real-image editing commonly relies on inversion and iterative sampling, while efficient one-step editors often stabilize a large update by estimating and averaging editing fields at multiple noise levels. We ask a stricter question: is a single temporal field evaluation sufficient for reliable inversion-free editing? Our answer rests on a previously underused duality in a variance-preserving (VP) one-step model: one source-target query at a shared noisy state simultaneously determines a local angular semantic tangent and a clean endpoint displacement. We integrate the tangent over the analytically known remaining VP angle to obtain a nominal one-step transport, and use the endpoint displacement to correct its long-horizon extrapolation through a constrained projection. This transport-first, correction-second construction yields Endpoint-Calibrated Transport (ECT), a closed-form, training-free editor requiring only one noise level, two text conditions packed into one denoiser batch, and one latent update. ECT requires no image inversion, trajectory integration, second temporal observation, or iterative optimization, and can be directly applied to pretrained epsilon-prediction VP one-step generators. Across the reported benchmark settings, ECT delivers stable gains in editing quality within an extremely short editing time.

cs.CV↗

arXiv2026

CAVC: Convergence-Adaptive Audio-Visual Cache for Modality-Asymmetric Diffusion Generation

Diffusion-based audio-visual generation methods typically perform joint denoising of audio and video latents throughout the entire sampling trajectory, repeatedly executing modality-specific denoising branches and cross-modal attention at every timestep. However, we observe that such uniform joint computation is not always necessary. The key is a modality-asymmetric recoverability: audio-side drift introduced by mid-stage caching can be substantially reduced by only a few terminal joint denoising steps, whereas video-side degradation caused by caching leads to persistent loss of motion and temporal details. This asymmetry suggests that inference acceleration should selectively cache recoverable audio-side computation while preserving full video refinement. Motivated by this observation, we propose \textbf{Convergence-Adaptive Audio-Visual Cache (CAVC)}, a training-free modality-asymmetric caching framework. CAVC adopts a sandwich-structured computation allocation: after detecting that audio denoiser outputs enter a cache-tolerant regime, it caches and reuses the audio denoiser output to bypass audio denoising and cross-modal attention in the middle stage, while the video branch continues independent spatio-temporal refinement; a few joint steps are then restored at the end to reduce accumulated cross-modal drift and improve synchronization. Experiments across multiple public benchmarks demonstrate that CAVC achieves 1.10--1.35x wall-clock acceleration, improves several visual dynamics and temporal statistics, and maintains competitive audio fidelity and audio-visual alignment.

cs.CV↗

arXiv2025

Video Virtual Try-on with Conditional Diffusion Transformer Inpainter

Video virtual try-on aims to naturally fit a garment to a target person in consecutive video frames. It is a challenging task, on the one hand, the output video should be in good spatial-temporal consistency, on the other hand, the details of the given garment need to be preserved well in all the frames. Naively using image-based try-on methods frame by frame can get poor results due to severe inconsistency. Recent diffusion-based video try-on methods, though very few, happen to coincide with a similar solution: inserting temporal attention into image-based try-on model to adapt it for video try-on task, which have shown improvements but there still exist inconsistency problems. In this paper, we propose ViTI (Video Try-on Inpainter), formulate and implement video virtual try-on as a conditional video inpainting task, which is different from previous methods. In this way, we start with a video generation problem instead of an image-based try-on problem, which from the beginning has a better spatial-temporal consistency. Specifically, at first we build a video inpainting framework based on Diffusion Transformer with full 3D spatial-temporal attention, and then we progressively adapt it for video garment inpainting, with a collection of masking strategies and multi-stage training. After these steps, the model can inpaint the masked garment area with appropriate garment pixels according to the prompt with good spatial-temporal consistency. Finally, as other try-on methods, garment condition is added to the model to make sure the inpainted garment appearance and details are as expected. Both quantitative and qualitative experimental results show that ViTI is superior to previous works.

cs.CV↗

arXiv2020

Class-Aware Domain Adaptation for Improving Adversarial Robustness

Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models to make a mistake. To improve the adversarial robustness of neural networks, adversarial training has been proposed to train networks by injecting adversarial examples into the training data. However, adversarial training could overfit to a specific type of adversarial attack and also lead to standard accuracy drop on clean images. To this end, we propose a novel Class-Aware Domain Adaptation (CADA) method for adversarial defense without directly applying adversarial training. Specifically, we propose to learn domain-invariant features for adversarial examples and clean images via a domain discriminator. Furthermore, we introduce a class-aware component into the discriminator to increase the discriminative power of the network for adversarial examples. We evaluate our newly proposed approach using multiple benchmark datasets. The results demonstrate that our method can significantly improve the state-of-the-art of adversarial robustness for various attacks and maintain high performances on clean images.

cs.CV↗

arXiv2019

Dual Adaptive Pyramid Network for Cross-Stain Histopathology Image Segmentation

Supervised semantic segmentation normally assumes the test data being in a similar data domain as the training data. However, in practice, the domain mismatch between the training and unseen data could lead to a significant performance drop. Obtaining accurate pixel-wise label for images in different domains is tedious and labor intensive, especially for histopathology images. In this paper, we propose a dual adaptive pyramid network (DAPNet) for histopathological gland segmentation adapting from one stain domain to another. We tackle the domain adaptation problem on two levels: 1) the image-level considers the differences of image color and style; 2) the feature-level addresses the spatial inconsistency between two domains. The two components are implemented as domain classifiers with adversarial training. We evaluate our new approach using two gland segmentation datasets with H&E and DAB-H stains respectively. The extensive experiments and ablation study demonstrate the effectiveness of our approach on the domain adaptive segmentation task. We show that the proposed approach performs favorably against other state-of-the-art methods.

cs.CV↗

arXiv2019

Learning Deep Image Priors for Blind Image Denoising

Image denoising is the process of removing noise from noisy images, which is an image domain transferring task, i.e., from a single or several noise level domains to a photo-realistic domain. In this paper, we propose an effective image denoising method by learning two image priors from the perspective of domain alignment. We tackle the domain alignment on two levels. 1) the feature-level prior is to learn domain-invariant features for corrupted images with different level noise; 2) the pixel-level prior is used to push the denoised images to the natural image manifold. The two image priors are based on $\mathcal{H}$-divergence theory and implemented by learning classifiers in adversarial training manners. We evaluate our approach on multiple datasets. The results demonstrate the effectiveness of our approach for robust image denoising on both synthetic and real-world noisy images. Furthermore, we show that the feature-level prior is capable of alleviating the discrepancy between different level noise. It can be used to improve the blind denoising performance in terms of distortion measures (PSNR and SSIM), while pixel-level prior can effectively improve the perceptual quality to ensure the realistic outputs, which is further validated by subjective evaluation.

eess.IV↗

arXiv2019

Look, Investigate, and Classify: A Deep Hybrid Attention Method for Breast Cancer Classification

One issue with computer based histopathology image analysis is that the size of the raw image is usually very large. Taking the raw image as input to the deep learning model would be computationally expensive while resizing the raw image to low resolution would incur information loss. In this paper, we present a novel deep hybrid attention approach to breast cancer classification. It first adaptively selects a sequence of coarse regions from the raw image by a hard visual attention algorithm, and then for each such region it is able to investigate the abnormal parts based on a soft-attention mechanism. A recurrent network is then built to make decisions to classify the image region and also to predict the location of the image region to be investigated at the next time step. As the region selection process is non-differentiable, we optimize the whole network through a reinforcement approach to learn an optimal policy to classify the regions. Based on this novel Look, Investigate and Classify approach, we only need to process a fraction of the pixels in the raw image resulting in significant saving in computational resources without sacrificing performances. Our approach is evaluated on a public breast cancer histopathology database, where it demonstrates superior performance to the state-of-the-art deep learning approaches, achieving around 96\% classification accuracy while only 15% of raw pixels are used.

cs.CV↗

arXiv2018

An End-to-End Deep Learning Histochemical Scoring System for Breast Cancer Tissue Microarray

One of the methods for stratifying different molecular classes of breast cancer is the Nottingham Prognostic Index Plus (NPI+) which uses breast cancer relevant biomarkers to stain tumour tissues prepared on tissue microarray (TMA). To determine the molecular class of the tumour, pathologists will have to manually mark the nuclei activity biomarkers through a microscope and use a semi-quantitative assessment method to assign a histochemical score (H-Score) to each TMA core. Manually marking positively stained nuclei is a time consuming, imprecise and subjective process which will lead to inter-observer and intra-observer discrepancies. In this paper, we present an end-to-end deep learning system which directly predicts the H-Score automatically. Our system imitates the pathologists' decision process and uses one fully convolutional network (FCN) to extract all nuclei region (tumour and non-tumour), a second FCN to extract tumour nuclei region, and a multi-column convolutional neural network which takes the outputs of the first two FCNs and the stain intensity description image as input and acts as the high-level decision making mechanism to directly output the H-Score of the input TMA image. To the best of our knowledge, this is the first end-to-end system that takes a TMA image as input and directly outputs a clinical score. We will present experimental results which demonstrate that the H-Scores predicted by our model have very high and statistically significant correlation with experienced pathologists' scores and that the H-Score discrepancy between our algorithm and the pathologists is on par with the inter-subject discrepancy between the pathologists.

cs.CV↗