10 2023 档案

效果超棒！Facebook AI 提出一种从文本描述生成三维动态场景的方法！
摘要：https://zhuanlan.zhihu.com/p/602067535 阅读全文
posted @ 2023-10-31 19:26 郭新晨 阅读(18) 评论(0) 推荐(0) 编辑
Text-to-3D Generation
摘要：https://blog.csdn.net/DUDUDUTU/article/details/129745399 阅读全文
posted @ 2023-10-31 19:25 郭新晨 阅读(5) 评论(0) 推荐(0) 编辑
【论文精读】Text-To-4D Dynamic Scene Generation
摘要：https://blog.csdn.net/m0_60634555/article/details/130321081 阅读全文
posted @ 2023-10-31 19:25 郭新晨 阅读(18) 评论(0) 推荐(0) 编辑
ProlificDreamer：高保真度和多样化的文本到3D模型生成方法，论文详解
摘要：https://zhuanlan.zhihu.com/p/633296390 阅读全文
posted @ 2023-10-31 19:24 郭新晨 阅读(44) 评论(0) 推荐(0) 编辑
Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields
摘要：https://eckertzhang.github.io/Text2NeRF.github.io/ 阅读全文
posted @ 2023-10-31 19:24 郭新晨 阅读(16) 评论(0) 推荐(0) 编辑
Text-To-4D Dynamic Scene Generation
摘要：https://make-a-video3d.github.io/ 阅读全文
posted @ 2023-10-31 19:23 郭新晨 阅读(6) 评论(0) 推荐(0) 编辑
Reconstructing compact building models from point clouds using deep implicit fields
摘要：https://github.com/chenzhaiyu/points2poly 阅读全文
posted @ 2023-10-31 17:32 郭新晨 阅读(17) 评论(0) 推荐(0) 编辑
Kitware's system for 3D building reconstruction for the IARPA CORE3D program
摘要：https://github.com/Kitware/Danesfield 阅读全文
posted @ 2023-10-31 17:31 郭新晨 阅读(11) 评论(0) 推荐(0) 编辑
implementation of "BS3D: Building-scale 3D Reconstruction from RGB-D Images"
摘要：https://github.com/jannemus/BS3D 阅读全文
posted @ 2023-10-31 17:30 郭新晨 阅读(7) 评论(0) 推荐(0) 编辑
3D reconstruction of buildings from a set of images taken from different points of view (frontal images of the façades and aerial images).
摘要：https://github.com/zhuhaipeng-byte/3D-Reconstruction-of-Urban-Scenes 阅读全文
posted @ 2023-10-31 17:30 郭新晨 阅读(4) 评论(0) 推荐(0) 编辑
We perform 3D reconstruction of buildings from sets of images of urban scenes taken from different points of view.
摘要：https://github.com/alvaro-budria/3D-Recovery-of-Urban-Scenes 阅读全文
posted @ 2023-10-31 17:29 郭新晨 阅读(3) 评论(0) 推荐(0) 编辑
High-Resolution 3D Human Digitization from A Single Image
摘要：https://github.com/facebookresearch/pifuhd 阅读全文
posted @ 2023-10-31 17:09 郭新晨 阅读(4) 评论(0) 推荐(0) 编辑
Single Image Indoor Scene Reconstruction
摘要：https://github.com/Amuseum-WHR/Single-Image-Indoor-Scene-Reconstruction 阅读全文
posted @ 2023-10-31 13:25 郭新晨 阅读(2) 评论(0) 推荐(0) 编辑
多模态3D理解的新篇章：ULIP（CVPR2023）与 ULIP-2
摘要：https://zhuanlan.zhihu.com/p/636635262 阅读全文
posted @ 2023-10-31 09:25 郭新晨 阅读(58) 评论(0) 推荐(0) 编辑
Implementation of CVPR'20 Oral: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
摘要：https://github.com/GAP-LAB-CUHK-SZ/Total3DUnderstanding 阅读全文
posted @ 2023-10-31 09:07 郭新晨 阅读(6) 评论(0) 推荐(0) 编辑
[CVPR 2023] DPE: Disentanglement of Pose and Expression for General Video Portrait Editing
摘要：https://github.com/OpenTalker/DPE 阅读全文
posted @ 2023-10-16 13:39 郭新晨 阅读(28) 评论(0) 推荐(0) 编辑
PyTorch implementation for Head2Head and Head2Head++. It can be used to fully transfer the head pose, facial expression and eye movements from a source video to a target identity.
摘要：https://github.com/michaildoukas/head2head 阅读全文
posted @ 2023-10-13 15:52 郭新晨 阅读(8) 评论(0) 推荐(0) 编辑
Transfer the facial expression of any human to the face of a target person
摘要：https://github.com/robinhesse/gan_transforming_faces 阅读全文
posted @ 2023-10-09 22:14 郭新晨 阅读(4) 评论(0) 推荐(0) 编辑
Real-time Facial Expression Transfer --> facial expression capture and reenactment via webcam
摘要：https://github.com/alina1021/facial_expression_transfer 阅读全文
posted @ 2023-10-09 22:14 郭新晨 阅读(5) 评论(0) 推荐(0) 编辑
Dynamic Programming and Optimal Control
摘要：https://www.mit.edu/~dimitrib/dpbook.html 阅读全文
posted @ 2023-10-08 11:11 郭新晨 阅读(9) 评论(0) 推荐(0) 编辑

点击右上角即可分享
微信分享提示