Searcharxiv⌕ Search

arXiv subjects

Junyan Cao

Publications and source records attributed to Junyan Cao.

At least 19 recordsLinked to original sources
arXiv2026

A flatness criterion for pseudo-effective sheaves on compact K\"ahler spaces

In this paper, we prove that if $E$ is a pseudo-effective sheaf with vanishing first Chern class on a klt compact K\"ahler space $X$, then, after passing to a finite quasi-\'etale cover, the reflexive pullback of $E$ is locally free and flat. This extends the flatness criterion of H\"oring--Peternell, originally established for projective varieties, to the K\"ahler setting. The proof relies on two main ingredients, both of which are new even in the projective case. The first is a flatness theorem for stable sheaves: we show that a slope-stable pseudo-effective sheaf with vanishing first Chern class is Hermitian flat. This is obtained by combining Hermitian--Einstein theory with the subharmonicity properties of direct image sheaves. The second is a singular K\"ahler analogue of Simpson's flatness theorem for extensions of locally free Hermitian flat sheaves.

math.AG↗
arXiv2026

NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods

In this paper, we review the NTIRE 2026 challenge on single-image reflection removal (SIRR) in the wild. SIRR is a fundamental task in image restoration. Despite progress in academic research, most methods are tested on synthetic images or limited real-world images, creating a gap in real-world applications. In this challenge, we provide participants with the OpenRR-5k dataset. This dataset requires participants to process real-world images covering a range of reflection scenarios and intensities, aiming to generate clean images without reflections. The challenge attracted more than 100 registrations, with eleven of them participating in the final testing phase. The top-ranked methods advanced the state-of-the-art reflection removal performance and earned unanimous recognition from five experts in the field. The proposed OpenRR-5k dataset is available at https://huggingface.co/datasets/qiuzhangTiTi/OpenRR-5k, and the homepage of this challenge is at https://github.com/caijie0620/OpenRR-5k.

cs.CV↗
arXiv2026

Two-step nilpotent monodromy of local systems on special varieties

Let $X$ be a smooth complex quasi-projective variety that is special in the sense of Campana. We prove that the monodromy group of any complex local system on $X$ is virtually nilpotent of class at most $2$. This result sharply refines a theorem of Cadorel, Yamanoi, and the second author. To establish this result, we develop a deformation theory for certain local systems on quasi-compact K\"ahler manifolds by constructing universal deformations for such local systems. As a byproduct of our argument, we also show that a general fiber of the quasi-Albanese map of $X$ is special, extending a result of Campana and Claudon from the projective to the quasi-projective setting.

math.AG↗
arXiv2026

Hodge theory for twisted log-differential forms

In this survey, we review recent developments in extending Hodge theory to differential forms with values in bundles equipped with singular metrics, based on joint work with Ya Deng, Christopher D. Hacon, and Mihai P\u{a}un.

math.CV↗
arXiv2025

Hodge theory for local systems and cohomological support loci

In this article, we pursue two main objectives. The first is to show that the fundamental results of Green-Lazarsfeld (1987, 1991) on generic vanishing theorems, and works of Budur-Wang (2015, 2020) on cohomology jumping loci, can be established within a unified framework based on suitable versions of the $\partial\bar{\partial}$-lemma. Our second-and primary-goal is to develop the technical tools required for this approach, namely an $L^2$-Hodge theory for the cohomology of rank-one local systems on quasi-compact K\"ahler manifolds. Further developments concerning higher-rank local systems, as well as several geometric applications, will be presented in a companion paper and are briefly outlined in the introduction.

math.AG↗
arXiv2024

Geometry of $K$-trivial Moishezon manifolds : decomposition theorem and holomorphic geometric structures

Let $X$ be a compact complex manifold such that its canonical bundle $K_X$ is numerically trivial. Assume additionally that $X$ is Moishezon or $X$ is Fujiki with dimension at most four. Using the MMP and classical results in foliation theory, we prove a Beauville-Bogomolov type decomposition theorem for $X$. We deduce that holomorphic geometric structures of affine type on $X$ are in fact locally homogeneous away from an analytic subset of complex codimension at least two, and that they cannot be rigid unless $X$ is an étale quotient of a compact complex torus. Moreover, we establish a characterization of torus quotients using the vanishing of the first two Chern classes which is valid for any compact complex $n$-folds of algebraic dimension at least $n-1$. Finally, we show that a compact complex manifold with trivial canonical bundle bearing a rigid geometric structure must have infinite fundamental group if either $X$ is Fujiki, $X$ is a threefold, or $X$ is of algebraic dimension at most one.

math.DG↗
arXiv2024

Diverse Image Harmonization

Image harmonization aims to adjust the foreground illumination in a composite image to make it harmonious. The existing harmonization methods can only produce one deterministic result for a composite image, ignoring that a composite image could have multiple plausible harmonization results due to multiple plausible reflectances. In this work, we first propose a reflectance-guided harmonization network, which can achieve better performance with the guidance of ground-truth foreground reflectance. Then, we also design a diverse reflectance generation network to predict multiple plausible foreground reflectances, leading to multiple plausible harmonization results. The extensive experiments on the benchmark datasets demonstrate the effectiveness of our method.

cs.CV↗
arXiv2024

Hermite--Einstein metrics in singular settings

In this article we pursue the following main goals. In the first place, we establish the existence of "estimable" Hermite--Einstein metrics for stable reflexive coherent sheaves on compact normal Kähler spaces. If moreover the background variety has klt singularities, we obtain a much more precise result.

math.DG↗
arXiv2024

Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling

Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadows for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset, we create a large-scale dataset called RdSOBA with rendering techniques. Moreover, we design a two-stage network named DMASNet with decomposed mask prediction and attentive shadow filling. Specifically, in the first stage, we decompose shadow mask prediction into box prediction and shape prediction. In the second stage, we attend to reference background shadow pixels to fill the foreground shadow. Abundant experiments prove that our DMASNet achieves better visual effects and generalizes well to real composite images.

cs.CV↗
arXiv2023

Painterly Image Harmonization by Learning from Painterly Objects

Given a composite image with photographic object and painterly background, painterly image harmonization targets at stylizing the composite object to be compatible with the background. Despite the competitive performance of existing painterly harmonization works, they did not fully leverage the painterly objects in artistic paintings. In this work, we explore learning from painterly objects for painterly image harmonization. In particular, we learn a mapping from background style and object information to object style based on painterly objects in artistic paintings. With the learnt mapping, we can hallucinate the target style of composite object, which is used to harmonize encoder feature maps to produce the harmonized image. Extensive experiments on the benchmark dataset demonstrate the effectiveness of our proposed method.

cs.CV↗
arXiv2023

Progressive Painterly Image Harmonization from Low-level Styles to High-level Styles

Painterly image harmonization aims to harmonize a photographic foreground object on the painterly background. Different from previous auto-encoder based harmonization networks, we develop a progressive multi-stage harmonization network, which harmonizes the composite foreground from low-level styles (e.g., color, simple texture) to high-level styles (e.g., complex texture). Our network has better interpretability and harmonization performance. Moreover, we design an early-exit strategy to automatically decide the proper stage to exit, which can skip the unnecessary and even harmful late stages. Extensive experiments on the benchmark dataset demonstrate the effectiveness of our progressive harmonization network.

cs.CV↗
arXiv2023

Painterly Image Harmonization via Adversarial Residual Learning

Image compositing plays a vital role in photo editing. After inserting a foreground object into another background image, the composite image may look unnatural and inharmonious. When the foreground is photorealistic and the background is an artistic painting, painterly image harmonization aims to transfer the style of background painting to the foreground object, which is a challenging task due to the large domain gap between foreground and background. In this work, we employ adversarial learning to bridge the domain gap between foreground feature map and background feature map. Specifically, we design a dual-encoder generator, in which the residual encoder produces the residual features added to the foreground feature map from main encoder. Then, a pixel-wise discriminator plays against the generator, encouraging the refined foreground feature map to be indistinguishable from background feature map. Extensive experiments demonstrate that our method could achieve more harmonious and visually appealing results than previous methods.

cs.CV↗
arXiv2023

Painterly Image Harmonization using Diffusion Model

Painterly image harmonization aims to insert photographic objects into paintings and obtain artistically coherent composite images. Previous methods for this task mainly rely on inference optimization or generative adversarial network, but they are either very time-consuming or struggling at fine control of the foreground objects (e.g., texture and content details). To address these issues, we propose a novel Painterly Harmonization stable Diffusion model (PHDiffusion), which includes a lightweight adaptive encoder and a Dual Encoder Fusion (DEF) module. Specifically, the adaptive encoder and the DEF module first stylize foreground features within each encoder. Then, the stylized foreground features from both encoders are combined to guide the harmonization process. During training, besides the noise loss in diffusion model, we additionally employ content loss and two style losses, i.e., AdaIN style loss and contrastive style loss, aiming to balance the trade-off between style migration and content preservation. Compared with the state-of-the-art models from related fields, our PHDiffusion can stylize the foreground more sufficiently and simultaneously retain finer content. Our code and model are available at https://github.com/bcmi/PHDiffusion-Painterly-Image-Harmonization.

cs.CV↗
arXiv2023

Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation

Given a composite image, image harmonization aims to adjust the foreground illumination to be consistent with background. Previous methods have explored transforming foreground features to achieve competitive performance. In this work, we show that using global information to guide foreground feature transformation could achieve significant improvement. Besides, we propose to transfer the foreground-background relation from real images to composite images, which can provide intermediate supervision for the transformed encoder features. Additionally, considering the drawbacks of existing harmonization datasets, we also contribute a ccHarmony dataset which simulates the natural illumination variation. Extensive experiments on iHarmony4 and our contributed dataset demonstrate the superiority of our method. Our ccHarmony dataset is released at https://github.com/bcmi/Image-Harmonization-Dataset-ccHarmony.

cs.CV↗
arXiv2023

Deep Image Harmonization with Learnable Augmentation

The goal of image harmonization is adjusting the foreground appearance in a composite image to make the whole image harmonious. To construct paired training images, existing datasets adopt different ways to adjust the illumination statistics of foregrounds of real images to produce synthetic composite images. However, different datasets have considerable domain gap and the performances on small-scale datasets are limited by insufficient training data. In this work, we explore learnable augmentation to enrich the illumination diversity of small-scale datasets for better harmonization performance. In particular, our designed SYthetic COmposite Network (SycoNet) takes in a real image with foreground mask and a random vector to learn suitable color transformation, which is applied to the foreground of this real image to produce a synthetic composite image. Comprehensive experiments demonstrate the effectiveness of our proposed learnable augmentation for image harmonization. The code of SycoNet is released at https://github.com/bcmi/SycoNet-Adaptive-Image-Harmonization.

cs.CV↗
arXiv2023

Painterly Image Harmonization in Dual Domains

Image harmonization aims to produce visually harmonious composite images by adjusting the foreground appearance to be compatible with the background. When the composite image has photographic foreground and painterly background, the task is called painterly image harmonization. There are only few works on this task, which are either time-consuming or weak in generating well-harmonized results. In this work, we propose a novel painterly harmonization network consisting of a dual-domain generator and a dual-domain discriminator, which harmonizes the composite image in both spatial domain and frequency domain. The dual-domain generator performs harmonization by using AdaIN modules in the spatial domain and our proposed ResFFT modules in the frequency domain. The dual-domain discriminator attempts to distinguish the inharmonious patches based on the spatial feature and frequency feature of each patch, which can enhance the ability of generator in an adversarial manner. Extensive experiments on the benchmark dataset show the effectiveness of our method. Our code and model are available at https://github.com/bcmi/PHDNet-Painterly-Image-Harmonization.

cs.CV↗
arXiv2023

Infinitesimal extension of pluricanonical forms

The current paper represents the first part: it contains the results concerning the lifting of twisted canonical sections defined on an infinitesimal neighborhood of the central fiber of a smooth, proper Kähler family which verify a natural L2 condition.

math.AG↗