Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks62 from public data
- Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images489
The proposed Neighbor2Neighbor framework is able to enjoy the progress of state-of-the-art supervised denoising networks in network architecture design and avoids heavy dependence on the assumption of the noise distribution.
- 461
- Video Super-Resolution with Recurrent Structure-Detail Network269
A novel recurrent video super-resolution method which is both effective and efficient in exploiting previous frames to super-resolve the current frame by dividing the input into structure and detail components which are fed to a recurrent unit composed of several proposed two-stream structure-detail blocks.
- Video Super-Resolution With Temporal Group Attention199
This work proposes a novel method that can effectively incorporate temporal information in a hierarchical way and achieves favorable performance against state-of-the-art methods on several benchmark datasets.
- Efficient Residual Dense Block Search for Image Super-Resolution152
An efficient residual dense block search algorithm with multiple objectives to hunt for fast, lightweight and accurate networks for image super-resolution models achieves better performance than the state-of-the-art methods with limited number of parameters and FLOPs.
- Exemplar Guided Unsupervised Image-to-Image Translation.146
The Exemplar Guided & Semantically Consistent Image-to-image Translation (EGSC-IT) network is proposed which conditions the translation process on an exemplar image in the target domain and introduces the concept of feature masks that provide coarse semantic guidance without requiring the use of any semantic labels.
- 125
- AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement121
The proposed AdaInt (Adaptive Intervals Learning) is a novel mechanism to achieve a more flexible sampling point allocation by adaptively learning the non-uniform sampling intervals in the 3D color space and is implemented as a compact and efficient plug-and-play module for a 3D LUT-based method.
- Motion Deblurring with Real Events120
An end-to-end learning framework for event-based motion deblurring in a self-supervised manner, where real-world events are exploited to alleviate the performance degradation caused by data inconsistency, and a piecewise linear motion model is proposed to take into account motion non-linearities.
- Co-Evolutionary Compression for Unpaired Image Translation93
A novel co-evolutionary approach for reducing their memory usage and FLOPs simultaneously and synergistically optimized for investigating the most important convolution filters iteratively is developed.
- CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation81
To overcome the scarcity of in-the-wild datasets with 3D object motion and camera pose annotations, this work carefully establish an automated data annotation pipeline that extracts 3D bounding boxes and camera trajectories from large-scale video data.
- 77
- Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling62
This paper proposes to compute the temporal difference between frames and divide those pixels into two subsets according to the level of difference and demonstrates the effectiveness of the proposed method and its favorable performance against state-of-the-art methods.
- 60
- 58
- Unsupervised Image Super-Resolution with an Indirect Supervised Path57
A novel framework which is composed of two stages: unsupervised image translation between real LR and synthetic LR images; and supervised super-resolution from approximated real LR images to the paired HR images, which achieves very good performance on datasets of NTIRE 2017, NTIRE 2018 and NTIRE 2020.
- 48
- 38
- GM-NeRF: Learning Generalizable Model-Based Neural Radiance Fields from Multi-View Images35
This work introduces an effective generalizable framework Generalizable Model-based Neural Radiance Fields (GM-NeRF) to synthesize free-viewpoint images and proposes a geometry-guided attention mechanism to register the appearance code from multi-view 2D images to a geometry proxy which can alleviate the misalignment between inaccurate geometry prior and pixel space.
- 30
- CharacterFactory: Sampling Consistent Characters With GANs for Diffusion Models25
This work proposes CharacterFactory, a framework that allows sampling new characters with consistent identities in the latent space of GANs for diffusion models, and considers the word embeddings of celeb names as ground truths for the identity-consistent generation task and trains a GAN model to learn the mapping from a latent space to the celeb embedding space.
- 19
- Perception-Oriented Bidirectional Attention Network for Image Super-Resolution Quality Assessment17
The Perception-oriented Bidirectional Attention Network (PBAN) for image SR FR-IQA is proposed, which is composed of three modules: an image encoder module, a perception-oriented bidirectional attention (PBA) module, and a quality prediction module that outperforms state-of-the-art quality assessment methods.
- MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models15
This work introduces a multimodal large language model (MLLM)-based recaptioner to expand the initial prompt to focus more on appearance and an appearance injection module to adapt appearance prior from video frames to the motion modeling process.
- Customizing Text-to-Image Generation with Inverted Interaction14
This work considers a novel concept customization task, that is, capturing the interaction between subjects in exemplar images and transferring the learned concept of interaction to achieve customized text-to-image generation.
- VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning12
VFXMaster is introduced, a unified, reference-based framework for VFX video generation that recasts effect generation as an in-context learning task, enabling it to reproduce diverse dynamic effects from a reference video onto target content and demonstrates remarkable generalization to unseen effect categories.
- Towards effective learning for face super-resolution with shape and pose perturbations12
This paper proposes to make use of the face-specific priors to enhance the performance of face super-resolution with the convolutional neural networks to impose perturbations on the low-dimensional space and generate face samples with novel appearance.
- Survey of Learning Based Single Image Super-Resolution Reconstruction Technology12
The paper systematically overviews this technology and discusses some main categories of it, such as super-resolution reconstruction based on neighbors, based on sparse representation,Based on deep learning, and future research directions for super- Resolution image reconstruction.
- ReNeg: Learning Negative Embedding with Reward Guidance11
ReNeg is introduced, an end-to-end method designed to learn improved Negative embeddings guided by a Reward model and shows that the learned negative embedding significantly outperforms null-text and handcrafted counterparts, achieving substantial improvements in human preference alignment.
- CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting11
This work proposes CCL-LGS, a novel framework that enforces view-consistent semantic supervision by integrating multi-view semantic cues and explicitly resolves semantic conflicts while preserving category discriminability.
- 11
- 10
- Style transfer network for complex multi-stroke text10
Experimental results show that the proposed text style transfer network outperforms state-of-the-art methods on both simple characters and complex multi-stroke characters, and increases the readability and aesthetics of the text.
- FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty8
Extensive experiments show that FoV-Net does not only extrapolate the temporally consistent wide field-of-view scene better than existing alternatives, but also provides the associated uncertainty which may benefit critical decision-making downstream applications.
- 7
- 7
- 6
- 5
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- Multi-granularity Transformer for Image Super-Resolution2
This work tackles image super-resolution by exploiting three transformer patterns, i.e. the window transformers, dilated transformers and global transformers, and proposes a Mu lti-g ranularity Trans former (MugFormer), which performs favorably against state-of-the-art methods in terms of both quantitative and qualitative results.
- 2
- 2
- 1
- 1
- 1
- Regularizing Subspace Redundancy of Low-Rank Adaptation1
ReSoRA theoretically decomposes the low-rank submatrices into multiple equivalent subspaces and systematically applies de-redundancy constraints to the feature distributions across different projections and systematically applies de-redundancy constraints to the feature distributions across different projections.
- Event-Guided Rolling Shutter Correction with Time-Aware Cross-Attentions1
The relationship between RS images and event data is modeled by incorporating time encoding to the computation of cross-attention in transformer encoder to achieve time-aware multi-modal information fusion in the rolling shutter correction (RSC) model.
- 1
- 1
- 1
- 1
- Perceptual Quality Assessment of Real-World Noise in Ultra-High-Definition Images–
PINE is proposed, a novel noise-oriented BIQA method that achieves state-of-the-art performance on the UNIQ-5k dataset and high rank consistency with PSNR and SSIM across the evaluated SIDD denoising results, showing that it may serve as an auxiliary no-reference indicator for restoration-oriented comparisons.
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. 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.