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/vegesm/depthpose
공식 코드Absolute Human Pose Estimation with Depth Prediction Network
https://github.com/vibot-lab/pola4all_jei_2023
공식 코드Pola4All: survey of polarimetric applications and an open-source toolkit to analyze polarization
https://github.com/vibot-lab/policalibration
공식 코드A Practical Calibration Method for RGB Micro-Grid Polarimetric Cameras
https://github.com/vico-uoe/mtpsl
공식 코드https://github.com/vincentfung13/MINE
공식 코드MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis
https://github.com/vinthony/depth-distillation
공식 코드https://github.com/vinvino02/GLPDepth
공식 코드Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth
https://github.com/vis-face/cdftn
공식 코드Cyclically Disentangled Feature Translation for Face Anti-spoofing
https://github.com/vis-var/lgsc-for-fas
공식 코드https://github.com/visinf/self-mono-sf
공식 코드https://github.com/vislearn/PrimeDepth
공식 코드PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage
https://github.com/vita-epfl/DFI-OmniStereo
공식 코드Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model
https://github.com/vita-epfl/Helvipad
공식 코드Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation
https://github.com/vita-epfl/monoloco
공식 코드MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation
https://github.com/vt-vl-lab/DF-Net
공식 코드DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency
https://github.com/w2kun/dcdepth
공식 코드DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain
https://github.com/w2kun/rnw
공식 코드Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
https://github.com/wang-xjtu/g2-monodepth
공식 코드G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB+X Data
https://github.com/wangjiyuan9/d4rd
공식 코드Digging into contrastive learning for robust depth estimation with diffusion models
https://github.com/wangjiyuan9/weatherdepth
공식 코드https://github.com/wangyueft/detr3d
공식 코드DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries
https://github.com/wangzhuo2019/ssan
공식 코드Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing
https://github.com/waymo-research/waymo-open-dataset
공식 코드LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection
https://github.com/wbkit/reslan
공식 코드https://github.com/wcy199705/dffinthewild
공식 코드https://github.com/weihaosky/MFuseNet
공식 코드Active Perception with A Monocular Camera for Multiscopic Vision
https://github.com/weiyithu/nerfingmvs
공식 코드NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
https://github.com/weiyithu/surrounddepth
공식 코드SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
https://github.com/wencheng256/daccn
공식 코드Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network
https://github.com/whu-usi3dv/osmloc
공식 코드https://github.com/wiktormucha/SHARP
공식 코드https://github.com/windysprint/uvz
공식 코드Underwater Variable Zoom: Depth-Guided Perception Network for Underwater Image Enhancement
https://github.com/wl-zhao/VPD
공식 코드Unleashing Text-to-Image Diffusion Models for Visual Perception
https://github.com/wolo-wolo/FSFM
공식 코드https://github.com/woxihuanjiangguo/bevnext
공식 코드BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.