https://github.com/GuidoManni/BodySLAM
공식 코드BodySLAM: A Generalized Monocular Visual SLAM Framework for Surgical Applications
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/HITSZ-NRSL/MSI-NeRF
공식 코드https://github.com/HKUST-Aerial-Robotics/Flow-Motion-Depth
공식 코드Flow-Motion and Depth Network for Monocular Stereo and Beyond
https://github.com/HMRC-AEL/MonoDEVSNet
공식 코드Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision
https://github.com/HalleyJiang/DiPE
공식 코드https://github.com/HeCraneChen/3D-Crowd-Pose-Estimation-Based-on-MVG
공식 코드Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry
https://github.com/Huangying-Zhan/Depth-VO-Feat
공식 코드https://github.com/HuynhLam/DAV
공식 코드Guiding Monocular Depth Estimation Using Depth-Attention Volume
https://github.com/IVRL/ComicsDepth
공식 코드https://github.com/IntelVCL/MultiObjectiveOptimization
공식 코드https://github.com/Ivanrs297/endoscopycorruptions
공식 코드EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth Prediction
https://github.com/JDAI-CV/faceX-Zoo
공식 코드Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning
https://github.com/JanRocketMan/regression-prior-networks
공식 코드https://github.com/JiaRenChang/PSMNet
공식 코드https://github.com/JiawangBian/sc_depth_pl
공식 코드Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
https://github.com/Jiawei-Yang/Denoising-ViT
공식 코드https://github.com/JiayuYANG/Self-supervised-CVP-MVSNet
공식 코드Self-supervised Learning of Depth Inference for Multi-view Stereo
https://github.com/JuanLuisGonzalez/PLADE-net
공식 코드https://github.com/JunjH/Boosting-Light-Weight-Depth-Estimation
공식 코드Boosting Light-Weight Depth Estimation Via Knowledge Distillation
https://github.com/JunjH/light-weight-depth-estimation
공식 코드Boosting Light-Weight Depth Estimation Via Knowledge Distillation
https://github.com/KU-CVLAB/DAG
공식 코드DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Models
https://github.com/KU-CVLAB/DaRF
공식 코드DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation
https://github.com/KaimingHe/resnet-1k-layers
공식 코드https://github.com/Kayaba-Akihiko/3DDX
공식 코드https://github.com/LacoLuo/RIS-Depth-Estimation
공식 코드Reconfigurable Intelligent Surface Aided Wireless Sensing for Scene Depth Estimation
https://github.com/Lavreniuk/SPIdepth
공식 코드SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation
https://github.com/LeoDarcy/GLPanoDepth
공식 코드https://github.com/LiheYoung/Depth-Anything
공식 코드Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
https://github.com/LinYark/Sdirt
공식 코드Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation
https://github.com/LiuJF1226/BDEdepth
공식 코드Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation
https://github.com/LukeLIN-web/VOTE
공식 코드VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting
https://github.com/MARSLab-UMN/DeepMultiviewDepth
공식 코드https://github.com/MARSLab-UMN/vi_depth_completion
공식 코드https://github.com/MI-Hussain/RVMDE
공식 코드RVMDE: Radar Validated Monocular Depth Estimation for Robotics
https://github.com/MMehdiMousavi/AIP
공식 코드AI Playground: Unreal Engine-based Data Ablation Tool for Deep Learning
https://github.com/MMehdiMousavi/SuperCaustics
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.