depth estimation/monocular CVPR task-related 个人记录

task-related CVPR depth estimation/monocular:

1. 《Unsupervised Monocular Depth Estimation with Left-Right Consistency》，2017，monodepth，无监督单目，创新loss，https://github.com/mrharicot/monodepth
2. 《Digging Into Self-Supervised Monocular Depth Estimation》，2019，monodepth2，自监督单目，创新loss，http://www.github.com/nianticlabs/monodepth2
3. 《MONOCULAR DEPTH ESTIMATION VIA LISTWISE RANKING USING THE PLACKETT-LUCE MODEL》，按远近策略排列物体，without github
4. 《AdaBins - Depth Estimation Using Adaptive Bins》，2020，回归问题转化为分类问题，分块预测，https://github.com/shariqfarooq123/AdaBins
5. 《Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration》，2021，输入双目通过数学建模和网络去模糊和重建图像，without github
6. 《Beyond Image to Depth - Improving Depth Prediction Using Echoes》，2021，结合回声和图像特征，多模态，https://krantiparida.github.io/projects/bimgdepth.html
7. 《Single Image Depth Prediction with Wavelet Decomposition》，2021，基于小波分解的单目深度预测网络，https://github.com/nianticlabs/wavelet-monodepth
8. 《PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss 》，自监督单目，网络结构和loss创新，without github
9. 《Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging》，2021，通过balance/tuning策略，融合利用其他最新单目预测网络结构，也加入场景理解，适用于高质量高分辨率图像的单目预测，without github
10. 《Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion》，2021，创新网络， https://github.com/TRI-ML/packnet-sfm
11. 《The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth》，2021，基于时序运动目标的自监督单目深度预测，创新网络结构和部分算法，https://github.com/nianticlabs/manydepth

not really task-related but useful:

1. 《Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks》，视频时序，with github
2. 《Three Ways To Improve Semantic Segmentation With Self-Supervised Depth Estimation》，利用单目深度估计来缓解训练语义分割网络需要大量数据的问题，with github
3. 《Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries》，新loss新插值方法补全深度，with github
4. 《Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation》，域适应学习深度预测与语义分割的关系，with github
5. 《Combined Depth Space based Architecture Search For Person Re-identification》，行人重识别创新轻量化网络结构和算法策略，without github