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/1hao-liu/sm4depth
공식 코드SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model
https://github.com/3dlg-hcvc/mirror3d
공식 코드https://github.com/3dperceptionlab/unrealrox
공식 코드https://github.com/3dperceptionlab/unrealrox-plus
공식 코드UnrealROX+: An Improved Tool for Acquiring Synthetic Data from Virtual 3D Environments
https://github.com/42Shawn/CMIM
공식 코드https://github.com/82magnolia/panoramic-depth-calibration
공식 코드Calibrating Panoramic Depth Estimation for Practical Localization and Mapping
https://github.com/AIRLabIISc/OceanLens
공식 코드https://github.com/AaltoVision/MaskMVS
공식 코드Unstructured Multi-View Depth Estimation Using Mask-Based Multiplane Representation
https://github.com/AbdelrhmanElnenaey/SIRR_MSloss_RefGAN_RDM
공식 코드Utilizing Multi-step Loss for Single Image Reflection Removal
https://github.com/Abdullah-Abuolaim/multi-task-defocus-deblurring-dual-pixel-nimat
공식 코드Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning
https://github.com/AdrienCourtois/neural-networks-properties
공식 코드Investigating Neural Architectures by Synthetic Dataset Design
https://github.com/AlaaLab/InstructCV
공식 코드InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists
https://github.com/AlessioQuercia/mdeaux
공식 코드Enhancing Monocular Depth Estimation with Multi-Source Auxiliary Tasks
https://github.com/AlexanderParkin/CASIA-SURF_CeFA
공식 코드https://github.com/AlmoonYsl/OPEN
공식 코드OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection
https://github.com/AnshShah3009/MetricGold
공식 코드MetricGold: Leveraging Text-To-Image Latent Diffusion Models for Metric Depth Estimation
https://github.com/Arnukk/CASPIAN
공식 코드https://github.com/Arthur151/ROMP
공식 코드https://github.com/Arthur151/Relative_Human
공식 코드Putting People in their Place: Monocular Regression of 3D People in Depth
https://github.com/AutoAILab/DynamicDepth
공식 코드Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth
https://github.com/AutoAILab/FusionDepth
공식 코드Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR
https://github.com/B1ueber2y/TrianFlow
공식 코드Towards Better Generalization: Joint Depth-Pose Learning without PoseNet
https://github.com/BFZD233/TranScene
공식 코드Multi-Label Stereo Matching for Transparent Scene Depth Estimation
https://github.com/BGUCompSci/WaveletCompressedConvolution
공식 코드https://github.com/BayesRays/BayesRays
공식 코드Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields
https://github.com/BiDAlab/mEBAL
공식 코드mEBAL: A Multimodal Database for Eye Blink Detection and Attention Level Estimation
https://github.com/BlueEg/back2color
공식 코드Back to the Color: Learning Depth to Specific Color Transformation for Unsupervised Depth Estimation
https://github.com/Bob-cheng/DepthModelHardening
공식 코드Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks
https://github.com/Bob-cheng/MDE_Attack
공식 코드Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
https://github.com/BrianPulfer/fsaa
공식 코드https://github.com/Brummi/BehindTheScenes
공식 코드Behind the Scenes: Density Fields for Single View Reconstruction
https://github.com/CVLAB-Unibo/ATDT
공식 코드https://github.com/CVLAB-Unibo/Learning2AdaptForStereo
공식 코드https://github.com/CVLAB-Unibo/Real-time-self-adaptive-deep-stereo
공식 코드https://github.com/CVLAB-Unibo/Semantic-Mono-Depth
공식 코드Geometry meets semantics for semi-supervised monocular depth estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.