- 博客(74)
- 收藏
- 关注
原创 3D Gaussian Splatting for Real-Time Radiance Field Rendering(慢慢啃,还是挺复杂的)
GS
2024-03-12 01:32:14 1007
原创 论文阅读:How Do Neural Networks See Depth in Single Images?
总结一下就是改变相机俯仰角和地平线位置对深度估计有影响但是影响不大。
2024-02-20 18:50:20 1250
原创 论文阅读: Semantics-guided Triplet Loss
一个度量学习方法,通过浏览语义引导的局部集合去优化内在深度表示。一个新颖的特征融合模块能有效利用跨模态特异质特征。
2024-01-02 04:01:17 597 1
原创 学习使用DDP: DistributedDataParallel
WORLD_SIZE:总进程数量,通常每个进程都会被分配一个唯一的 rank,而 world_size 就是所有进程的总数量。和:这两个环境变量用于指定主进程的地址和端口号。在分布式训练中,主进程通常用于协调其他进程的工作。LOCAL_RANK和LOCAL_SIZE: 这两个环境变量是 torch.distributed.launch 工具特有的,用于指定当前进程在本地节点上的 local_rank 和节点上 GPU 的总数量 local_size。RANK和WORLD_SIZE。
2023-12-18 02:12:58 1015
原创 论文阅读:Fast-BEV: Towards Real-time On-vehicleBird’s-Eye View Perception
M2BEVq∈Pxyzkv∈F2Duv。
2023-10-12 15:34:16 152
原创 论文阅读:AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation
[1] Huang S W, Lin C T, Chen S P, et al. Auggan: Cross domain adaptation with gan-based data augmentation[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 718-731.
2023-09-22 10:45:36 400
原创 论文笔记:Reinforcing Local Structure Perception for Monocular Depth Estimation
在m个不同尺度上采样三个点。
2023-09-07 11:15:30 166
原创 论文阅读:SERE: Exploring Feature Self-relation for Self-supervised Transformer
使用自监督学习为卷积网络(CNN)学习表示已经被验证对视觉任务有效。作为CNN的一种替代方案,视觉变换器(ViT)具有强大的表示能力,具有空间自注意力和通道级前馈网络。最近的研究表明,自监督学习有助于释放ViT的巨大潜力。然而,大多数研究仍然遵循为CNN设计的自监督策略,例如实例级别的样本区分,但它们忽视了ViT的特性。我们观察到,关于空间和通道维度的关系建模使ViT与其他网络有所不同。为了强化这一特性,我们探索了特征自关系(SElf-RElation,SERE)来训练自监督ViT。
2023-09-05 22:29:06 540
原创 论文阅读:Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
我们定义一个模型fff, 输入xxx输出aaa。-定义每一个Task -TTT包含一个损失函数LLL, 一个原始观察qx1q(x_1)qx1, 一个状态转移分布qx1∣xtatqx1∣xtat以及集长度HHH。在监督任务中H=1(也就是说当前的a只和当前的x有关)。在我们的元学习场景中,我们考虑了一个跨任务的分布pTp(T)pT,我们希望我们的模型能够适应这个分布。
2023-08-26 11:30:36 1155
原创 论文笔记Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision
Ψθ;x→dθ∗minθLθ;XrXsYs)Xrxtrt1NrNrXsxtst1NsNrΨθ;x)Ψθ;x)θencθpyrθdecLLsfθVsf;XrLspθXs;YsLDAθencVDA;XrXs)LsfθVsf;Xr)LspθXs;Ys)dtsp≥dma。
2023-07-11 20:22:14 116 2
原创 论文阅读:Dense Depth Priors for Neural Radiance Fields from Sparse Input Views
CVPR2022。
2023-06-19 22:16:35 1825 2
原创 论文阅读:Scale-aware and High Quality Monocular Depth Estimation Without Real World Labels
CVPR2022
2023-06-15 14:58:12 66
原创 论文笔记:Normalizing Flows for Probabilistic Modeling and Inference
Normalizing Flow 笔记
2023-06-05 11:41:55 933 1
原创 论文阅读: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Driving
对FS-Dpeth的记录
2023-05-23 21:38:19 79 1
原创 论文阅读: NeRF−−: Neural Radiance Fields Without Known Camera Parameters
NeRF−−: Neural Radiance Fields Without Known Camera Parameters
2023-03-07 23:17:27 361
原创 论文阅读:Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
2023-03-04 18:32:12 717
原创 论文阅读:MPViT : Multi-Path Vision Transformer for Dense Prediction
MPViT : Multi-Path Vision Transformer for Dense Prediction
2023-03-01 11:08:36 789
原创 论文阅读:Self-Supervised Monocular Depth Estimation with Internal Feature Fusion(DIFFNet)
Self-Supervised Monocular Depth Estimation with Internal Feature Fusion
2023-02-28 16:36:39 592 1
原创 论文阅读:NeRF++: ANALYZING AND IMPROVING NEURAL RADIANCE FIELDS
NeRF++: ANALYZING AND IMPROVING NEURAL RADIANCE FIELDS
2023-02-27 11:22:28 486
原创 论文阅读:RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation
RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation
2023-02-22 14:33:45 527 4
原创 论文阅读:pixelNeRF: Neural Radiance Fields from One or Few Images
pixelNeRF: Neural Radiance Fields from One or Few Images
2023-02-20 22:17:07 444
原创 论文阅读:InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering
InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering
2023-02-20 15:43:36 748 1
原创 论文笔记:RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
2023-02-17 22:13:30 350
原创 论文笔记:NeuLF: Efficient Novel View Synthesis with Neural 4D Light Fight
NeuLF: Efficient Novel View Synthesis with Neural 4D Light Fight
2023-02-15 21:12:42 399 1
原创 论文笔记:Vision Transformers for Dense Prediction
Vision Transformers for Dense Prediction
2023-02-15 10:50:06 650
原创 论文笔记: Monocular Depth Estimation: a Review of the 2022 State of the Art
Monocular Depth Estimation: a Review of the 2022 State of the Art
2023-02-14 13:20:21 717 4
原创 论文阅读:GeoAug: Data Augmentation for Few-Shot NeRF with Geometry Constrain
GeoAug: Data Augmentation for Few-Shot NeRF with Geometry Constrain
2023-02-13 21:57:45 404
原创 论文阅读:MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthes
MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthes
2023-02-11 10:40:01 568
原创 论文笔记:NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
2023-02-09 15:30:13 267 1
原创 论文笔记:Depth-supervised NeRF: Fewer Views and Faster Training for Free
Depth-supervised NeRF: Fewer Views and Faster Training for Free
2023-02-08 21:11:34 981
原创 论文笔记:D-NeRF:Neural Radiance Fields for Dynamic Scenes
D-NeRF:Neural Radiance Fields for Dynamic Scenes
2023-02-07 23:04:36 1053 3
原创 论文笔记:HR-Depth:High Resolution Self-Supervised Monocular Depth Estimation
HR-Depth:High Resolution Self-Supervised Monocular Depth Estimation
2023-02-07 14:46:28 751 1
原创 论文笔记:Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation
Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation
2023-02-07 10:39:30 277 1
原创 论文笔记:Space-time Neural Irradiance Fields for Free-Viewpoint Video
Space-time Neural Irradiance Fields for Free-Viewpoint Video
2023-02-06 21:48:31 509 1
原创 Ubuntu16.04搭建深度学习环境
安装显卡驱动查看显卡型号lspci | grep -i vga下载显卡驱动卸载原系统中的Nvidia驱动。sudo apt-get remove --purge nvidia*禁用nouveausudo gedit /etc/modprobe.d/blacklist.conf在最后添加代码段:blacklist vga16fbblacklist nouveaublacklist rivafbblacklist rivatvblacklist nvidiafb
2022-04-29 16:36:30 255
原创 2021-11-27 笔记 (时间戳)
1.python加入时间戳import datetimetimestamp = datetime.datetime.now().strftime("%m-%d-%H:%M)
2022-03-04 10:19:32 456
原创 anconda 创建迁移虚拟环境(pack)
安装conda-packpip install conda-pack打包Ubuntu系统下的环境conda pack -n env_name#若不记得环境名称,用 conda env list 命令查看将生成的 env_name.tar.gz文件上传至服务器。并在anaconda/env/目录下解压。tar -xzvf env_name.tar.gz -C /way/to/anaconda/env/env_name...
2022-02-16 11:13:22 959
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人