2023.04.07 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(shí)間有限,本專欄無(wú)法做文章的講解,只挑選出符合PaperABC研究興趣和當(dāng)前熱點(diǎn)問(wèn)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97篇
2D vision
SegGPT: Segmenting Everything In Context
https://arxiv.org/pdf/2304.03284.pdf

智源曹越組的工作。汝比那Seg Anything又如何?下手晚了一天?。?br>
AIGC
LANe : Lighting-Aware Neural Fields for Compositional Scene Synthesis
https://arxiv.org/pdf/2304.03280.pdf

又是一篇組合性的場(chǎng)景合成工作。
Neural Fields meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes
https://arxiv.org/pdf/2304.03266.pdf

多倫多大學(xué)Sanja組的工作,NeRF和顯式幾何表征的相遇。應(yīng)該是未來(lái)的熱點(diǎn)了。
Inst-Inpaint: Instructing to Remove Objects with Diffusion Models
https://arxiv.org/pdf/2304.03246.pdf

文本引導(dǎo)的圖像上物體remove工作。
SKETCHFFUSION: SKETCH-GUIDED IMAGE EDITING WITH DIFFUSION MODEL
https://arxiv.org/pdf/2304.03174.pdf

浙江大學(xué)的工作,基于草圖的圖像編輯工作。
Synthesizing Anyone, Anywhere, in Any Pose
https://arxiv.org/pdf/2304.03164.pdf

現(xiàn)在的工作真是五花八門啊