Papers with Code 아카이브
Depth Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 10
- 평가표
- 14
- 보존된 평가 기록
- 58
Depth Estimation is the task of measuring the distance of each pixel relative to the camera. Depth is extracted from either monocular (single) or stereo (multiple views of a scene) images. Traditional methods use multi-view geometry to find the relationship between the images. Newer methods can directly estimate depth by minimizing the regression loss, or by learning to generate a novel view from a sequence. The most popular benchmarks are KITTI and NYUv2. Models are typically evaluated according to a RMS metric.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/manurare/360monodepth
360MonoDepth: High-Resolution 360° Monocular Depth Estimation
https://github.com/marcobellagente93/Bayesian_Regression
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
https://github.com/marload/ConvNets-TensorFlow2
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/marrlab/dinobloom
https://github.com/martius-lab/beta-nll
https://github.com/masoudnick/brain-tumor-mri-classification
https://github.com/matakshay/Neural_Image_Caption_Generator
https://github.com/matsuren/omnimvs_pytorch
OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching
https://github.com/maxwelltsai/DeepGalaxy
https://github.com/mbsariyildiz/resnet-pytorch
https://github.com/mdda/deep-learning-models
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/mega-sam/mega-sam
MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
https://github.com/megvii-research/basecls/tree/main/zoo/public/resnet
https://github.com/megvii-research/basecls/tree/main/zoo/public/vgg
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/meteorshowers/StereoNet
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
https://github.com/meteorshowers/X-StereoLab
HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching
https://github.com/mgonzalezrivero/reef_learning
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/mhagiwara/nanigonet
https://github.com/microsoft/fb.resnet.torch
https://github.com/mikekestemont/deepscript
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/mindlab-ai/mindcv/blob/main/examples/train_cifar_dynamic.py
https://github.com/mindlab-ai/mindcv/blob/main/mindcv/models/resnet.py
https://github.com/mindlab-ai/mindcv/blob/main/mindcv/models/vgg.py
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/mindspore-ai/models/tree/master/official/cv/depthnet
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
https://github.com/mindspore-ai/models/tree/master/official/cv/resnet
https://github.com/mindspore-ai/models/tree/master/official/cv/resnet50_quant
https://github.com/mindspore-ai/models/tree/master/official/cv/resnet_thor
https://github.com/mindspore-ai/models/tree/master/official/cv/vgg16
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/mindspore-ai/models/tree/master/research/cv/FaceAttribute
https://github.com/mindspore-ai/models/tree/master/research/cv/adelaide_ea
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
https://github.com/mindspore-ai/models/tree/master/research/cv/midas
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer
https://github.com/mindspore-ai/models/tree/master/research/cv/vgg19
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/resnet.py
https://github.com/mindspore-courses/MindSpore-classification
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/mindspore-courses/heads-on-mindspore/tree/main/1-best-practice/models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.