Lune

学者档案2022-2026

Zhanyu Ma

Beijing University of Posts and Telecommunications

21论文数
12末位作者
54合作者人数
0一作
0独著

一作与末位作者按论文署名顺序统计,部分顶会采用姓氏字母顺序署名。

近期论文21

  1. Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance第 5 位,共 5 位作者AAAI 2026 · 4 次引用
  2. Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers第 11 位,共 11 位作者ICLR 2026 · 1 次引用
  3. Reversing the Flow: Generation-to-Understanding Synergy in Large Multimodal Models第 6 位,共 6 位作者CVPR Findings 2026
  4. Small Object, Great Challenge: A Benchmark for Small Object Visual Grounding第 5 位,共 6 位作者CVPR 2026
  5. PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction第 8 位,共 8 位作者ICCV 2025 · 2 次引用
  6. FairHuman: Boosting Hand and Face Quality in Human Image Generation with Minimum Potential Delay Fairness in Diffusion Models第 5 位,共 5 位作者ICCV 2025 · 1 次引用
  7. ConMo: Controllable Motion Disentanglement and Recomposition for Zero-Shot Motion Transfer第 6 位,共 8 位作者CVPR 2025
  8. PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction第 5 位,共 5 位作者CVPR 2025
  9. Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network第 6 位,共 7 位作者ACM MM 2024 · 77 次引用
  10. Dual-Prior Augmented Decoding Network for Long Tail Distribution in HOI Detection第 5 位,共 6 位作者AAAI 2024 · 14 次引用
  11. Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding第 6 位,共 8 位作者NeurIPS 2024 · 13 次引用
  12. Channel-Spatial Support-Query Cross-Attention for Fine-Grained Few-Shot Image Classification第 4 位,共 5 位作者ACM MM 2024 · 12 次引用
  13. Benchmarking Segmentation Models with Mask-Preserved Attribute Editing第 4 位,共 5 位作者CVPR 2024 · 2 次引用
  14. DemoFusion: Democratising High-Resolution Image Generation With No $$$第 5 位,共 5 位作者CVPR 2024
  15. NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images第 7 位,共 8 位作者CVPR 2024
  16. Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification第 5 位,共 8 位作者AAAI 2023 · 76 次引用
  17. Task-aware Adaptive Learning for Cross-domain Few-shot Learning第 6 位,共 6 位作者ICCV 2023 · 22 次引用
  18. Multi-View Active Fine-Grained Visual Recognition第 6 位,共 6 位作者ICCV 2023 · 14 次引用
  19. An Erudite Fine-Grained Visual Classification Model第 6 位,共 6 位作者CVPR 2023
  20. On-the-Fly Category Discovery第 6 位,共 6 位作者CVPR 2023
  21. Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction第 5 位,共 5 位作者ACM MM 2022 · 66 次引用
黄昏的海面,两侧是细线勾勒的悬崖