ECCV 2020 超分辨率方向上接收文章總結(持續更新)

ECCV 2020

ECCV是European Conference on Computer Vision的縮寫,即歐洲計算機視覺大會。今年第16屆ECCV原定於2020年8月23-28日在英國格拉斯哥舉行。

ECCV 2020 已經放榜,有效投稿數爲5025,最終收錄1361篇論文,錄取率是27%。其中104篇 Oral、161篇 Spotlights,其餘的均爲Poster。現將超分辨率方向上接收的文章總結如下。總結有遺漏的地方還請各位讀者幫忙指出。

圖像超分辨率

  1. Invertible Image Rescaling
  1. Component Divide-and-Conquer for Real-World Image Super-Resolution
  2. SRFlow: Learning the Super-Resolution Space with Normalizing Flow (Spotlight)
  3. Single Image Super-Resolution via a Holistic Attention Network
  4. Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks
  5. LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block
  6. VarSR: Variational Super-Resolution Network for Very Low Resolution Images
  7. Learning with Privileged Information for Efficient Image Super-Resolution
  8. Journey Towards Tiny Perceptual Super-Resolution

視頻超分辨率

  1. MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution
  2. Video Super-Resolution with Recurrent Structure-Detail Network

零/小樣本

  1. Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning
  2. Fast Adaptation to Super-Resolution Networks via Meta-Learning

人臉超分辨率

  1. Face Super-Resolution Guided by 3D Facial Priors (Spotlight)

其他場景超分辨率

  1. Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal Learning
  2. Texture Hallucination for Large-Factor Painting Super-Resolution
  3. Scene Text Image Super-Resolution in the Wild
  4. Spatial-Angular Interaction for Light Field Image Super-Resolution
  1. Towards Content-independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation
  2. PAMS: Quantized Super-Resolution via Parameterized Max Scale
  3. Mining self-similarity: Label super-resolution with epitomic representations
  4. Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution

參考資料

  1. ECCV 2020 放榜!一文看盡10篇論文的開源項目(檢測/GAN/SR等方向)
  2. ECCV2020-Code
  3. ECCV 官方接收名單
發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章