https://github.com/CVLAB-Unibo/Unsupervised_Depth_Adaptation
공식 코드Unsupervised Domain Adaptation for Depth Prediction from Images
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/CVLAB-Unibo/omeganet
공식 코드Distilled Semantics for Comprehensive Scene Understanding from Videos
https://github.com/CapsuleEndoscope/EndoSLAM
공식 코드https://github.com/CapsuleEndoscope/VirtualCapsuleEndoscopy
공식 코드https://github.com/ClementPinard/depth-dataset-builder
공식 코드https://github.com/CompVis/depth-fm
공식 코드https://github.com/Daniel-xsy/RoboBEV
공식 코드Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving
https://github.com/DarthReca/depth-any-canopy
공식 코드Depth Any Canopy: Leveraging Depth Foundation Models for Canopy Height Estimation
https://github.com/Davidyao99/uni4d
공식 코드Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
https://github.com/Davidzhangyuanhan/CelebA-Spoof
공식 코드CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations
https://github.com/DepthAnything/Depth-Anything-V2
공식 코드https://github.com/DepthAnything/PromptDA
공식 코드Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation
https://github.com/DepthComputation/InSpaceType_Benchmark
공식 코드InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimation
https://github.com/Div99/W-Stereo-Disp
공식 코드https://github.com/DrSleep/multi-task-refinenet
공식 코드Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
https://github.com/ENSTA-U2IS-AI/Multimodal_Deep_segmentation
공식 코드InfraParis: A multi-modal and multi-task autonomous driving dataset
https://github.com/ENSTA-U2IS-AI/torch-uncertainty
공식 코드https://github.com/EPFL-VILAB/MultiMAE
공식 코드https://github.com/EPFL-VILAB/Omnidata
공식 코드Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans
https://github.com/EPFL-VILAB/XTConsistency
공식 코드https://github.com/EdwardSmith1884/3D-Object-Super-Resolution
공식 코드Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation
https://github.com/EdwardSmith1884/Multi-View-Silhouette-and-Depth-Decomposition-for-High-Resolution-3D-Object-Representation
공식 코드Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation
https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DINO
공식 코드Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning
https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DPT
공식 코드Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning
https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-Segmenter
공식 코드Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning
https://github.com/Eyeline-Research/FlashDepth
공식 코드FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution
https://github.com/F-Barto/LiDARTouch
공식 코드LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR
https://github.com/Faceplugin-ltd/FaceLivenessDetection-Android
공식 코드Generalized Face Liveness Detection via De-fake Face Generator
https://github.com/FengQiaojun/TerrainMesh
공식 코드Mesh Reconstruction from Aerial Images for Outdoor Terrain Mapping Using Joint 2D-3D Learning
https://github.com/FilippoAleotti/Reversing
공식 코드Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation
https://github.com/FilippoAleotti/mobilePydnet
공식 코드Real-time single image depth perception in the wild with handheld devices
https://github.com/FrancisXZhang/DAEVI
공식 코드https://github.com/GaochangWu/DA2N
공식 코드Revisiting Light Field Rendering with Deep Anti-Aliasing Neural Network
https://github.com/Garsonjw/AdvFAS
공식 코드AdvFAS: A robust face anti-spoofing framework against adversarial examples
https://github.com/GhiXu/ACMP
공식 코드https://github.com/Gradiant/bob.paper.icb2019.gradgpad
공식 코드Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.