https://github.com/ifnspaml/SGDepth
공식 코드Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
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/ifnspaml/advattackdet
공식 코드Detecting Adversarial Perturbations in Multi-Task Perception
https://github.com/indu1ge/DepthMaster
공식 코드DepthMaster: Taming Diffusion Models for Monocular Depth Estimation
https://github.com/innovator-zero/MTDP_Lib
공식 코드https://github.com/insta360-research-team/defom-stereo
공식 코드https://github.com/intel-isl/MiDaS
공식 코드Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer
https://github.com/intellabs/mmpano
공식 코드L-MAGIC: Language Model Assisted Generation of Images with Coherence
https://github.com/irfanICMLL/structure_knowledge_distillation
공식 코드https://github.com/irmvlab/3dunmonoflow
공식 코드Unsupervised Learning of 3D Scene Flow from Monocular Camera
https://github.com/iro-cp/FCRN-DepthPrediction
공식 코드Deeper Depth Prediction with Fully Convolutional Residual Networks
https://github.com/ishikaalunawat/231aproj
공식 코드https://github.com/ishmav16/Dual-CNN-Models-for-Unsupervised-Monocular-Depth-Estimation
공식 코드https://github.com/isl-cv/chitransformer
공식 코드https://github.com/isl-org/MiDaS
공식 코드MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
https://github.com/isl-org/ZoeDepth
공식 코드ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
https://github.com/isl-org/vi-depth
공식 코드https://github.com/ivrl/ai4va
공식 코드Unlocking Comics: The AI4VA Dataset for Visual Understanding
https://github.com/ixilai/mfif-mmif
공식 코드https://github.com/jadgardner/ns_reni
공식 코드RENI++ A Rotation-Equivariant, Scale-Invariant, Natural Illumination Prior
https://github.com/jarvishou829/sups
공식 코드SUPS: A Simulated Underground Parking Scenario Dataset for Autonomous Driving
https://github.com/jeffwang987/asap
공식 코드Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark
https://github.com/jeffwang987/movedepth
공식 코드Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning
https://github.com/jerukan/barrels
공식 코드Leveraging 6DoF Pose Foundation Models For Mapping Marine Sediment Burial
https://github.com/jerukan/poseidon
공식 코드Leveraging 6DoF Pose Foundation Models For Mapping Marine Sediment Burial
https://github.com/jhornauer/embedded_domain_adaptation
공식 코드Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware
https://github.com/jhornauer/grumodepth
공식 코드https://github.com/jhornauer/mde_ood
공식 코드Out-of-Distribution Detection for Monocular Depth Estimation
https://github.com/jiahaoLjh/HumanDepth
공식 코드HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization
https://github.com/jiahaoLjh/PlaneSweepPose
공식 코드Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo
https://github.com/jianfeij/monomvsnet
공식 코드MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network
https://github.com/jianfenglihg/Unsupervised_geometry
공식 코드Unsupervised Joint Learning of Depth, Optical Flow, Ego-motion from Video
https://github.com/jianwang-mpi/SceneEgo
공식 코드https://github.com/jiaxiZeng/Temporally-Consistent-Stereo-Matching
공식 코드https://github.com/jiaxiangshang/MGCNet
공식 코드Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency
https://github.com/jiayuyang/consistnet
공식 코드ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion
https://github.com/jieqianyu/sgn
공식 코드Camera-based 3D Semantic Scene Completion with Sparse Guidance Network
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.