2023.04.04 ArXiv精選
關(guān)注領(lǐng)域：
AIGC
3D computer vision learning
Fine-grained learning
GNN
其他
聲明
論文較多，時間有限，本專欄無法做文章的講解，只挑選出符合PaperABC研究興趣和當(dāng)前熱點問題相關(guān)的論文，如果你的research topic和上述內(nèi)容有關(guān)，那本專欄可作為你的論文更新源或Paper reading list．
Paper list:
今日ArXiv共更新151篇
AIGC
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
https://arxiv.org/pdf/2304.01186.pdf
騰訊的工作，視頻領(lǐng)域的controlNet.
Robust Text-driven Image Editing Method that Adaptively Explores Directions in Latent Spaces of StyleGAN and CLIP
https://arxiv.org/pdf/2304.00964.pdf
文本驅(qū)動的圖像編輯方法.
DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models
https://arxiv.org/pdf/2304.00916.pdf
太卷了，太卷了，自己看吧，朋友們。
VLP
Vision-Language Models for Vision Tasks: A Survey
https://arxiv.org/pdf/2304.00685.pdf
視覺語言預(yù)訓(xùn)練模型的最新綜述
RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
https://arxiv.org/pdf/2304.00962.pdf
區(qū)域級別的點云和文本的對比學(xué)習(xí)，主要用于open-world的3D場景理解。
AirLoc: Object-based Indoor Relocalization
https://arxiv.org/pdf/2304.00954.pdf
CMU的室內(nèi)場景定位工作.
Multi-Modal Representation Learning with Text-Driven Soft Masks
https://arxiv.org/pdf/2304.00719.pdf
