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/lppllppl920/EndoscopyDepthEstimation-Pytorch
공식 코드Dense Depth Estimation in Monocular Endoscopy with Self-supervised Learning Methods
https://github.com/ltu-machine-learning/analysis-of-deep-perceptual-loss-networks
공식 코드https://github.com/luigifreda/pyslam
공식 코드pySLAM: An Open-Source, Modular, and Extensible Framework for SLAM
https://github.com/lukasliebel/MultiDepth
공식 코드MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification
https://github.com/lustoo/fghv
공식 코드Feature Generation and Hypothesis Verification for Reliable Face Anti-Spoofing
https://github.com/lyndonzheng/Synthetic2Realistic
공식 코드T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks
https://github.com/lyp-deeplearning/liftfeat
공식 코드https://github.com/macrohuang1993/ESNet
공식 코드https://github.com/madhubabuv/NightDepthADFA
공식 코드https://github.com/madhubabuv/dtd
공식 코드Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models
https://github.com/magicleap/DELTAS
공식 코드DELTAS: Depth Estimation by Learning Triangulation And densification of Sparse points
https://github.com/malga-vision/co-semdepth
공식 코드Co-SemDepth: Fast Joint Semantic Segmentation and Depth Estimation on Aerial Images
https://github.com/marcelampc/d3net_depth_estimation
공식 코드Deep Depth from Defocus: how can defocus blur improve 3D estimation using dense neural networks?
https://github.com/markusschoen/mgnet
공식 코드MGNet: Monocular Geometric Scene Understanding for Autonomous Driving
https://github.com/markyu98/madpose
공식 코드Relative Pose Estimation through Affine Corrections of Monocular Depth Priors
https://github.com/matsuren/crownconv360depth
공식 코드https://github.com/mattpoggi/3net
공식 코드Learning monocular depth estimation with unsupervised trinocular assumptions
https://github.com/mattpoggi/depthstillation
공식 코드https://github.com/mattpoggi/mono-uncertainty
공식 코드On the uncertainty of self-supervised monocular depth estimation
https://github.com/mattpoggi/pydnet
공식 코드Towards real-time unsupervised monocular depth estimation on CPU
https://github.com/maturk/dn-splatter
공식 코드DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing
https://github.com/maximedieudonne/dpf-star
공식 코드$DPF^*$: improved Depth Potential Function for scale-invariant sulcal depth estimation
https://github.com/maybelx/mvsformerplusplus
공식 코드MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo
https://github.com/mayechi/lt3d-lf
공식 코드https://github.com/mbar0075/object-detection-correlation-saliency-vs-depth
공식 코드Correlation of Object Detection Performance with Visual Saliency and Depth Estimation
https://github.com/meder411/MappedConvolutions
공식 코드https://github.com/mediabrain-sjtu/coca3d
공식 코드https://github.com/mediaeng-lfv/LFV_Disparity_Estimation
공식 코드https://github.com/megvii-basedetection/bevdepth
공식 코드BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection
https://github.com/megvii-basedetection/bevstereo
공식 코드BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo
https://github.com/megvii-research/sparse-beats-dense
공식 코드Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion
https://github.com/mengyuest/SIGNet
공식 코드SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception
https://github.com/mercerai/evggs
공식 코드EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting
https://github.com/mhamilton723/FeatUp
공식 코드FeatUp: A Model-Agnostic Framework for Features at Any Resolution
https://github.com/mic-rud/guideddecoding
공식 코드Lightweight Monocular Depth Estimation through Guided Decoding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.