NSTL国家科技图书文献中心

1. Event-Adapted Video Super-Resolution NSTL国家科技图书文献中心

Zeyu Xiao | Dachun Kai ... - 《Computer Vision - ECCV 2024,Part XLII》 - European Conference on Computer Vision - 2025, - 217～235 - 共19页

摘要：Introducing event cameras into video super | -resolution* (VSR) shows great promise. In practice, however* | , integrating event data as a new modality necessitates a | laborious model architecture design. This not only | consumes substantial time and effort but also disregards

关键词： Video super-Resolution | Event camera | Parameter-Efficient tuning | Vision adapter

2. Reference-Based Face Super-Resolution Using the Spatial Transformer NSTL国家科技图书文献中心

Varun Ramesh Jois | Antonella DiLillo ... - 《Computer Vision - ACCV 2024,Part IV》 - Asian Conference on Computer Vision - 2025, - 409～425 - 共17页

摘要：Face super-resolution* is the task of* | increasing the resolution* of an image containing a face* | present a reference-based solution for face super | -resolution* that uses higher resolution reference images to* | thereby adding finer detail. It is a ubiquitous task in

关键词： Reference-Based super-Resolution | Face super-Resolution | Image alignment

3. Dynamic Window Transformer for Image Super-Resolution NSTL国家科技图书文献中心

Zheng Xie | Zhongxun Wang ... - 《Computer Vision - ACCV 2024,Part VII》 - Asian Conference on Computer Vision - 2025, - 435～449 - 共15页

摘要：Image super-resolution* (SR) reconstruction is* | generate high-resolution (HR) images from low-resolution | a critical task in image processing that aims to | (LR) inputs. Recently, Swin-Transformer-based models | have become mainstream in this field due to their

关键词： Super-Resolution | Dynamic-Window self-Attention | Transformer

4. Residual Hybrid Attention Enhanced Video Super-Resolution with Cross Convolution NSTL国家科技图书文献中心

Shiqian Yuan | Boyue Li ... - 《Pattern Recognition and Computer Vision,Part VI》 - Chinese Conference on Pattern Recognition and Computer Vision - 2025, - 535～549 - 共15页

摘要：In video super-resolution* reconstruction* | Attention-Enhanced Video Super-Resolution* Model, augmented* | , traditional methods often fall short in capturing details | , particularly in edges and occluded areas, which affects the | realism and clarity of the images. To address this issue

关键词： Video super-resolution | Hybrid attention | Cross convolution

5. Complementary Dual-Branch Network for Space-Time Video Super-Resolution NSTL国家科技图书文献中心

Ming Tian | Tianyi Li ... - 《Pattern Recognition,Part XXXII》 - International Conference on Pattern Recognition - 2025, - 182～195 - 共14页

摘要：Space-time video super-resolution* aims to* | , predominantly achieving space-time video super-resolution | video super-resolution* and video frame interpolation* | enhancement between video super-resolution* and video frame* | Deformable Alignment into space-time video super-resolution

关键词： Feature aggregation | Feature interpolation | Space-time video super-resolution

6. PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution NSTL国家科技图书文献中心

Yan Wang | Yusen Li ... - 《Computer Vision - ACCV 2024,Part IV》 - Asian Conference on Computer Vision - 2025, - 246～264 - 共19页

摘要： super-resolution (SR) research. While recent progress | Reducing latency is a roaring trend in recent | exploits various convolutional blocks, attention modules | , and backbones to unlock the full potentials of the | convolutional neural network (ConvNet), achieving real-time

关键词： Super-resolution | Reparamterization | Attention

7. Face to Cartoon Incremental Super-Resolution Using Knowledge Distillation NSTL国家科技图书文献中心

Trinetra Devkatte | Shiv Ram Dubey ... - 《Pattern Recognition,Part VII》 - International Conference on Pattern Recognition - 2025, - 99～114 - 共16页

摘要：Facial super-resolution/hallucination is an | super-resolution while retaining the learned knowledge | -resolution* facial images for a variety of applications* | addresses this problem by proposing an incremental super | -resolution* using GANs with knowledge distillation (ISR-KD*

关键词： Knowledge distillation | Incremental learning | Face to cartoon super-Resolution

8. Mamba-Based Light Field Super-Resolution with Efficient Subspace Scanning NSTL国家科技图书文献中心

Ruisheng Gao | Zeyu Xiao ... - 《Computer Vision - ACCV 2024,Part V》 - Asian Conference on Computer Vision - 2025, - 421～437 - 共17页

摘要： Super-Resolution method, named MLFSR, by designing an | impressive performance in 4D light field (LF) super | -resolution* by effectively modeling long-range spatial* | hinders the efficient processing of high resolution* 4D* | -resolution* 4D LFs with enhanced performance. Our code is*

关键词： Light field | Super-resolution | State space model

9. Edge-Enhanced Super-Resolution Reconstruction of Rock CT Images NSTL国家科技图书文献中心

Chennian Gao | Chen Qiu - 《Pattern Recognition and Computer Vision,Part IX》 - Chinese Conference on Pattern Recognition and Computer Vision - 2025, - 276～289 - 共14页

摘要： this issue, this paper proposes a super-resolution | feature modulation for efficient image super-resolution | convolutional neural network-based super-resolution* methods* | , acquiring high-resolution* CT images of rocks with a larger* | Computed Tomography (CT) technology for rock

关键词： Rock CT images | Trainable sobel convolution | Edge enhancement | Super-resolution

10. MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution NSTL国家科技图书文献中心

Yuxuan Jiang | Chen Feng ... - 《Computer Vision - ECCV 2024,Part XXXIX》 - European Conference on Computer Vision - 2025, - 364～382 - 共19页

摘要： super-resolution, most KD approaches are modified | for image super-resolution* based on three popular* | super-resolution performance, up to 0.46 dB (based on | Distillation (MTKD) framework specifically for image super | -resolution. It exploits the advantages of multiple teachers

摘要：Introducing event cameras into video super | -resolution* (VSR) shows great promise. In practice, however* | , integrating event data as a new modality necessitates a | laborious model architecture design. This not only | consumes substantial time and effort but also disregards

关键词： Video super-Resolution | Event camera | Parameter-Efficient tuning | Vision adapter

摘要：Face super-resolution* is the task of* | increasing the resolution* of an image containing a face* | present a reference-based solution for face super | -resolution* that uses higher resolution reference images to* | thereby adding finer detail. It is a ubiquitous task in

关键词： Reference-Based super-Resolution | Face super-Resolution | Image alignment

摘要：Image super-resolution* (SR) reconstruction is* | generate high-resolution (HR) images from low-resolution | a critical task in image processing that aims to | (LR) inputs. Recently, Swin-Transformer-based models | have become mainstream in this field due to their

关键词： Super-Resolution | Dynamic-Window self-Attention | Transformer

摘要：In video super-resolution* reconstruction* | Attention-Enhanced Video Super-Resolution* Model, augmented* | , traditional methods often fall short in capturing details | , particularly in edges and occluded areas, which affects the | realism and clarity of the images. To address this issue

关键词： Video super-resolution | Hybrid attention | Cross convolution

摘要：Space-time video super-resolution* aims to* | , predominantly achieving space-time video super-resolution | video super-resolution* and video frame interpolation* | enhancement between video super-resolution* and video frame* | Deformable Alignment into space-time video super-resolution

关键词： Feature aggregation | Feature interpolation | Space-time video super-resolution

摘要： super-resolution (SR) research. While recent progress | Reducing latency is a roaring trend in recent | exploits various convolutional blocks, attention modules | , and backbones to unlock the full potentials of the | convolutional neural network (ConvNet), achieving real-time

关键词： Super-resolution | Reparamterization | Attention

摘要：Facial super-resolution/hallucination is an | super-resolution while retaining the learned knowledge | -resolution* facial images for a variety of applications* | addresses this problem by proposing an incremental super | -resolution* using GANs with knowledge distillation (ISR-KD*

关键词： Knowledge distillation | Incremental learning | Face to cartoon super-Resolution

摘要： Super-Resolution method, named MLFSR, by designing an | impressive performance in 4D light field (LF) super | -resolution* by effectively modeling long-range spatial* | hinders the efficient processing of high resolution* 4D* | -resolution* 4D LFs with enhanced performance. Our code is*

关键词： Light field | Super-resolution | State space model

摘要： this issue, this paper proposes a super-resolution | feature modulation for efficient image super-resolution | convolutional neural network-based super-resolution* methods* | , acquiring high-resolution* CT images of rocks with a larger* | Computed Tomography (CT) technology for rock

关键词： Rock CT images | Trainable sobel convolution | Edge enhancement | Super-resolution

摘要： super-resolution, most KD approaches are modified | for image super-resolution* based on three popular* | super-resolution performance, up to 0.46 dB (based on | Distillation (MTKD) framework specifically for image super | -resolution. It exploits the advantages of multiple teachers

关键词： Image super-Resolution | Knowledge distillation | Multi-teacher | MTKD

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：Introducing event cameras into video super | -resolution (VSR) shows great promise. In practice, however | , integrating event data as a new modality necessitates a | laborious model architecture design. This not only | consumes substantial time and effort but also disregards

关键词： Video super-Resolution | Event camera | Parameter-Efficient tuning | Vision adapter

摘要：Face super-resolution is the task of | increasing the resolution of an image containing a face | present a reference-based solution for face super | -resolution that uses higher resolution reference images to | thereby adding finer detail. It is a ubiquitous task in

关键词： Reference-Based super-Resolution | Face super-Resolution | Image alignment

摘要：Image super-resolution (SR) reconstruction is | generate high-resolution (HR) images from low-resolution | a critical task in image processing that aims to | (LR) inputs. Recently, Swin-Transformer-based models | have become mainstream in this field due to their

关键词： Super-Resolution | Dynamic-Window self-Attention | Transformer

摘要：In video super-resolution reconstruction | Attention-Enhanced Video Super-Resolution Model, augmented | , traditional methods often fall short in capturing details | , particularly in edges and occluded areas, which affects the | realism and clarity of the images. To address this issue

关键词： Video super-resolution | Hybrid attention | Cross convolution

摘要：Space-time video super-resolution aims to | , predominantly achieving space-time video super-resolution | video super-resolution and video frame interpolation | enhancement between video super-resolution and video frame | Deformable Alignment into space-time video super-resolution

关键词： Feature aggregation | Feature interpolation | Space-time video super-resolution

摘要： super-resolution (SR) research. While recent progress | Reducing latency is a roaring trend in recent | exploits various convolutional blocks, attention modules | , and backbones to unlock the full potentials of the | convolutional neural network (ConvNet), achieving real-time

关键词： Super-resolution | Reparamterization | Attention

摘要：Facial super-resolution/hallucination is an | super-resolution while retaining the learned knowledge | -resolution facial images for a variety of applications | addresses this problem by proposing an incremental super | -resolution using GANs with knowledge distillation (ISR-KD

关键词： Knowledge distillation | Incremental learning | Face to cartoon super-Resolution

摘要： Super-Resolution method, named MLFSR, by designing an | impressive performance in 4D light field (LF) super | -resolution by effectively modeling long-range spatial | hinders the efficient processing of high resolution 4D | -resolution 4D LFs with enhanced performance. Our code is

关键词： Light field | Super-resolution | State space model

摘要： this issue, this paper proposes a super-resolution | feature modulation for efficient image super-resolution | convolutional neural network-based super-resolution methods | , acquiring high-resolution CT images of rocks with a larger | Computed Tomography (CT) technology for rock

关键词： Rock CT images | Trainable sobel convolution | Edge enhancement | Super-resolution

摘要： super-resolution, most KD approaches are modified | for image super-resolution based on three popular | super-resolution performance, up to 0.46 dB (based on | Distillation (MTKD) framework specifically for image super | -resolution. It exploits the advantages of multiple teachers

关键词： Image super-Resolution | Knowledge distillation | Multi-teacher | MTKD

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：Introducing event cameras into video super | -resolution* (VSR) shows great promise. In practice, however* | , integrating event data as a new modality necessitates a | laborious model architecture design. This not only | consumes substantial time and effort but also disregards

摘要：Face super-resolution* is the task of* | increasing the resolution* of an image containing a face* | present a reference-based solution for face super | -resolution* that uses higher resolution reference images to* | thereby adding finer detail. It is a ubiquitous task in

摘要：Image super-resolution* (SR) reconstruction is* | generate high-resolution (HR) images from low-resolution | a critical task in image processing that aims to | (LR) inputs. Recently, Swin-Transformer-based models | have become mainstream in this field due to their

摘要：In video super-resolution* reconstruction* | Attention-Enhanced Video Super-Resolution* Model, augmented* | , traditional methods often fall short in capturing details | , particularly in edges and occluded areas, which affects the | realism and clarity of the images. To address this issue

摘要：Space-time video super-resolution* aims to* | , predominantly achieving space-time video super-resolution | video super-resolution* and video frame interpolation* | enhancement between video super-resolution* and video frame* | Deformable Alignment into space-time video super-resolution

摘要：Facial super-resolution/hallucination is an | super-resolution while retaining the learned knowledge | -resolution* facial images for a variety of applications* | addresses this problem by proposing an incremental super | -resolution* using GANs with knowledge distillation (ISR-KD*

摘要： Super-Resolution method, named MLFSR, by designing an | impressive performance in 4D light field (LF) super | -resolution* by effectively modeling long-range spatial* | hinders the efficient processing of high resolution* 4D* | -resolution* 4D LFs with enhanced performance. Our code is*

摘要： this issue, this paper proposes a super-resolution | feature modulation for efficient image super-resolution | convolutional neural network-based super-resolution* methods* | , acquiring high-resolution* CT images of rocks with a larger* | Computed Tomography (CT) technology for rock

摘要： super-resolution, most KD approaches are modified | for image super-resolution* based on three popular* | super-resolution performance, up to 0.46 dB (based on | Distillation (MTKD) framework specifically for image super | -resolution. It exploits the advantages of multiple teachers