2023.02.22 ArXiv精选

• 关注领域：

• AIGC
  

• 3D computer vision learning

• Fine-grained learning

• GNN

• 其他
  

• 声明
  

• 论文较多，时间有限，本专栏无法做文章的讲解，只挑选出符合PaperABC研究兴趣和当前热点问题相关的论文，如果你的research topic和上述内容有关，那本专栏可作为你的论文更新源或Paper reading list．

Paper list:

AIGC:

1. Composer: Creative and Controllable Image Synthesis with Composable Conditions

2. Learning 3D Photography Videos via Self-supervised Diffusion on Single Images

3. 3D-aware Conditional Image Synthesis

4. Text-driven Visual Synthesis with Latent Diffusion Prior

5. LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation

6. Learning 3D Photography Videos via Self-supervised Diffusion on Single Images

7. On Calibrating Diffusion Probabilistic Models

细粒度学习：

1. Semantic Feature Integration network for Fine-grained Visual Classification

3D 视觉：

1. MVFusion: Multi-View 3D Object Detection with Semantic-aligned Radar and Camera Fusion

2. Few-Shot Point Cloud Semantic Segmentation via Contrastive Self-Supervision and Multi-Resolution Attention

3. USR: Unsupervised Separated 3D Garment and Human Reconstruction via Geometry and Semantic Consistency

4. MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts

5. RealFusion 360◦ Reconstruction of Any Object from a Single Image

6. PC2 : Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction    

自监督学习：

1. Self-supervised learning of Split Invariant Equivariant representations