Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Alex Chichung KotSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works74 from public data
- Low-Light Image Enhancement with Normalizing Flow650
This paper investigates to model this one-to-many relationship via a proposed normalizing flow model of an invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution.
- 209
- CRRN: Multi-scale Guided Concurrent Reflection Removal Network137
This paper proposes the Concurrent Reflection Removal Network (CRRN), a network that integrates image appearance information and multi-scale gradient information with human perception inspired loss function, and is trained on a new dataset with 3250 reflection images taken under diverse real-world scenes.
- 135
- 100
- Learning Meta Pattern for Face Anti-Spoofing92
A learnable network to extract Meta Pattern (MP) and a two-stream network to hierarchically fuse the input RGB image and the extracted MP by using the proposed Hierarchical Fusion Module (HFM) are proposed.
- 82
- 79
- CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields60
This paper proposes to protect the copyright of NeRF models by replacing the original color representation in NeRF with a watermarked color representation, and a distortion-resistant rendering scheme is designed to guarantee robust message extraction in 2D renderings of NeRF.
- 48
- Benchmarking Single-Image Reflection Removal Algorithms46
This paper presents a SIngle-image Reflection Removal Plus dataset, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of-the-art (especially learning-based) methods.
- 43
- Heterogeneous Transfer Learning via Deep Matrix Completion with Adversarial Kernel Embedding42
This paper proposes a new HTL method based on a deep matrix completion framework, where kernel embedding of distributions is trained in an adversarial manner for learning heterogeneous features across domains.
- 41
- The Age of Synthetic Realities: Challenges and Opportunities40
The crucial need for the development of forensic techniques capable of identifying harmful synthetic creations and distinguishing them from reality is highlighted, especially important in scenarios involving the creation and dissemination of fake news, disinformation, and misinformation.
- Face Image Reflection Removal38
The face image reflection removal problem is solved by incorporating inpainting ideas into a guided reflection removal framework, which takes two images as the input and considers various face-specific priors.
- IDET: Iterative Difference-Enhanced Transformers for High-Quality Change Detection34
This paper proposes a novel module called the iterative difference-enhanced transformers (IDET), which consists of three transformers for extracting long-range information from the bi-temporal images, and one for enhancing the feature difference.
- 33
- 32
- Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning31
This paper proposes to learn a disentangled latent representation based on implicit autoencoders that is transferable across domains and demonstrates the effectiveness of this proposed method on digit recognition, object recognition and semantic segmentation.
- 29
- 29
- Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method With Forgery Style Mixture27
This work develops a parameter-efficient ViT-based detection model that includes lightweight forgery feature extraction modules and enables the model to extract global and local forgery clues simultaneously, representing an important step toward open-set Deepfake detection in the wild.
- 23
- The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fields20
This paper proposes NeRF Signature, a novel watermarking method for NeRF that employs a Codebook-aided Signature Embedding that does not alter the model structure, thereby maintaining imperceptibility and enhancing robustness at the model level.
- 17
- 15
- SPY-Watermark: Robust Invisible Watermarking for Backdoor Attack14
This work proposes a novel backdoor attack method named Spy-Watermark, which remains effective when facing data collapse and backdoor defense, and introduces a learnable watermark embedded in the latent domain of images, serving as the trigger.
- 14
- MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure13
GaussianBridge is introduced that transforms unstructured 3D Gaussians into Splatter Image format, enabling direct neural processing for arbitrary message embedding, and a Gaussian-Uncertainty-Perceptual heatmap prediction strategy for preserving visual quality.
- 13
- Unsupervised Domain Adaptation for Low-Dose CT Reconstruction via Bayesian Uncertainty Alignment13
This work proposes to leverage a probabilistic reconstruction framework to conduct a joint discrepancy minimization between source and target domains in both the latent and image spaces, and proposes a sharpness-aware distribution alignment (SDA) to achieve a match of second-order information.
- 13
- Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction11
Stereo-GS, a disentangled framework for efficient 3D Gaussian prediction, extracts features from local image pairs using a stereo vision backbone and fuses them via global attention blocks to achieve pose-free 3D reconstruction, improving robustness and practicality.
- 11
- 10
- 9
- 9
- 8
- MantleMark: Migrating Watermarks From Multi-View Images to Radiance Fields via Frequency Modulation6
MantleMark is proposed, a watermarking framework that migrates watermarks from multi-view images to radiance fields via frequency modulation via frequency modulation, and achieves robust watermark detection while maintaining high visual quality across various radiance field-based reconstruction methods.
- 6
- 6
- Unified Steganography via Implicit Neural Representation5
U-INR is presented, a novel method for steganography via Implicit Neural Representation (INR) that directly uses the neurons of the INR network to represent the secret data and cover data across different data types and introduces a key-based selection strategy that can be used to determine the position within the INRs for data storage.
- SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpainting5
The detail-enhanced attentional implicit representation (DEAR) is proposed that can achieve SuperInpaint with a single model, resulting in high-quality completed images with arbitrary resolutions and outperforms all existing methods on four widely used metrics.
- Removing Image Artifacts From Scratched Lens Protectors5
This work considers the inherent challenges in a unified framework with two cooperative modules, which facilitate the performance boost of each other, and demonstrates that the method outperforms the baselines qualitatively and quantitatively.
- 5
- 5
- Align 3D Representation and Text Embedding for 3D Content Personalization4
This work develops a camera-conditioned 3D-to-text inverse mechanism that projects 3D contents into a 3D embedding aligned with text embeddings that enables efficient manipulation and personalization of 3D content through natural language prompts, eliminating the need for computationally retraining procedures.
- 4
- 3
- 3
- 3
- See Through the Windshield from Surveillance Camera3
A windshield image restoration generative adversarial network (WIRE-GAN) to restore and enhance the visibility of windshield images and introduces a novel content-preserving strategy into the proposed weakly-supervised framework to generate more semantically consistent results.
- 3
- 2
- 1
- 1
- Quantum-Inspired Frequency Attenuation for Enhanced Targeted Fabrication Attacks in Object Detection1
- 1
- 1
- Asynchronous Event Error-Minimizing Noise for Safeguarding Event Dataset1
This work proposes the first unlearnable event stream generation method to prevent unauthorized training from event datasets, and proposes a new form of asynchronous event error-minimizing noise to perturb event streams, tricking the unauthorized model into learning embedded noise instead of realistic features.
- 1
- Enhancing Low-Light Images Using Infrared Encoded Images1
A novel approach to increase the visibility of images captured under low-light environments by removing the in-camera infrared (IR) cut-off filter, which allows for the capture of more photons and results in improved signal-to-noise ratio due to the inclusion of information from the IR spectrum.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Single-image reflection removal : from computational imaging to deep learning–
This thesis proposes a method to automatically detect the regions with and without reflections and process them in a heterogeneous manner and introduces a data-driven method by using the concurrent deep learning framework.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.