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/jingjin25/LFASR-geometry
공식 코드Learning Light Field Angular Super-Resolution via a Geometry-Aware Network
https://github.com/jingjin25/LFDE-OccUnNet
공식 코드Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields
https://github.com/jixingwu/sol-slam
공식 코드An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World
https://github.com/jiyuanfeng/ddp
공식 코드https://github.com/joe-siyuan-qiao/ViP-DeepLab
공식 코드ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
https://github.com/joelmoniz/DepthNets
공식 코드Unsupervised Depth Estimation, 3D Face Rotation and Replacement
https://github.com/johnminelli/twowaysynth
공식 코드Depth self-supervision for single image novel view synthesis
https://github.com/jonathanventura/cylindricalsfmlearner
공식 코드Unsupervised Learning of Depth and Ego-Motion from Cylindrical Panoramic Video
https://github.com/jspenmar/DeFeat-Net
공식 코드DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning
https://github.com/jspenmar/monodepth_benchmark
공식 코드Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter
https://github.com/jspenmar/slowtv_monodepth
공식 코드Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV
https://github.com/julilien/PLDepth
공식 코드Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce Model
https://github.com/jun0kim/dkn
공식 코드https://github.com/junda24/afnet
공식 코드Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving
https://github.com/junda24/monster
공식 코드https://github.com/junggy/hammer-dataset
공식 코드On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks
https://github.com/junyuandeng/dm-calib
공식 코드Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration
https://github.com/jwh97nn/DeepDPS
공식 코드Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning
https://github.com/jyjunmcl/Depth-Map-Decomposition
공식 코드https://github.com/jytime/Deep-SfM-Revisited
공식 코드https://github.com/jzhangbs/Vis-MVSNet
공식 코드https://github.com/jzr99/Geo4D
공식 코드Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
https://github.com/kakaxi314/GuideNet
공식 코드https://github.com/kamiLight/CADepth-master
공식 코드Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation
https://github.com/kangliao929/cylin-painting
공식 코드Cylin-Painting: Seamless {360\textdegree} Panoramic Image Outpainting and Beyond
https://github.com/keqpan/udsr
공식 코드https://github.com/kieran514/dyna-dm
공식 코드Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Maps
https://github.com/kmaag/Temporal-False-Negative-Reduction
공식 코드False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates
https://github.com/kmaag/fn-reduction-using-depth
공식 코드False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimation
https://github.com/koushiksrivats/flip
공식 코드FLIP: Cross-domain Face Anti-spoofing with Language Guidance
https://github.com/koutilya40192/SharinGAN
공식 코드SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation
https://github.com/krantiparida/beyond-image-to-depth
공식 코드Beyond Image to Depth: Improving Depth Prediction using Echoes
https://github.com/kritiksoman/GIMP-ML
공식 코드GIMP-ML: Python Plugins for using Computer Vision Models in GIMP
https://github.com/kspeng/lw-eg-monodepth
공식 코드https://github.com/ku-cvlab/maskingdepth
공식 코드MaskingDepth: Masked Consistency Regularization for Semi-supervised Monocular Depth Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.