https://github.com/tensorflow/models/tree/master/research/vid2depth
공식 코드Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints
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/theia-4869/bicross
공식 코드Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer
https://github.com/thetna/endo-active-learn
공식 코드https://github.com/thuzhaowang/idn-solver
공식 코드A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo
https://github.com/tiancuteqy/endoomni
공식 코드https://github.com/tim885/P2ORM
공식 코드Pixel-Pair Occlusion Relationship Map(P2ORM): Formulation, Inference & Application
https://github.com/timmh/synthetic-animals
공식 코드https://github.com/tinghuiz/SfMLearner
공식 코드https://github.com/tiny-smart/dysample
공식 코드https://github.com/tiny-smart/sapa
공식 코드https://github.com/toastydom/net2brain
공식 코드Net2Brain: A Toolbox to compare artificial vision models with human brain responses
https://github.com/towardsautonomy/VR3Dense
공식 코드https://github.com/tri-ml/dd3d
공식 코드https://github.com/truongkhang/cds-mvsnet
공식 코드Curvature-guided dynamic scale networks for Multi-view Stereo
https://github.com/tsunghan-wu/depth-completion
공식 코드Indoor Depth Completion with Boundary Consistency and Self-Attention
https://github.com/tub-rip/dvs_mcemvs
공식 코드Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion
https://github.com/tudelft/filled-disparity-monodepth
공식 코드Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes
https://github.com/turagalab/snapshotscope
공식 코드FourierNets enable the design of highly non-local optical encoders for computational imaging
https://github.com/twhui/rm-depth
공식 코드RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes
https://github.com/twke18/Adversarial_Structure_Matching
공식 코드Adversarial Structure Matching for Structured Prediction Tasks
https://github.com/ucaszyp/steps
공식 코드STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation
https://github.com/udaykusupati/Normal-Assisted-Stereo
공식 코드https://github.com/uddd821/hv-bev
공식 코드HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection
https://github.com/uf-robopi/udepth
공식 코드UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robots
https://github.com/ukcheolshin/bridgemultispectraldepth
공식 코드Bridging Spectral-wise and Multi-spectral Depth Estimation via Geometry-guided Contrastive Learning
https://github.com/ukcheolshin/supdepth4thermal
공식 코드Deep Depth Estimation from Thermal Image: Dataset, Benchmark, and Challenges
https://github.com/ukcheolshin/thermalmonodepth
공식 코드https://github.com/umarKarim/cou_sfm
공식 코드https://github.com/umarKarim/cou_stereo
공식 코드https://github.com/urancon/stereospike
공식 코드https://github.com/uzh-rpg/rpg_e2depth
공식 코드https://github.com/uzh-rpg/rpg_ramnet
공식 코드https://github.com/val-iisc/gd-uap
공식 코드Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations
https://github.com/valeoai/LaRa
공식 코드LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation
https://github.com/valeoai/WoodScape
공식 코드WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving
https://github.com/valeoai/WoodScape/tree/master/omnidet
공식 코드OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.