https://github.com/yaqding/pose_monodepth
공식 코드RePoseD: Efficient Relative Pose Estimation With Known Depth Information
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/yasaminjafarian/HDNet_TikTok
공식 코드Self-supervised 3D Representation Learning of Dressed Humans from Social Media Videos
https://github.com/yfujimura/DCV-release
공식 코드https://github.com/ygjwd12345/TransDepth
공식 코드Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction
https://github.com/ygjwd12345/VISTA-Net
공식 코드Variational Structured Attention Networks for Deep Visual Representation Learning
https://github.com/yhZhai/idol
공식 코드IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation
https://github.com/yhw-yhw/PVAMVSNet
공식 코드Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation
https://github.com/yichen928/geal_active_learning
공식 코드https://github.com/yifliu3/EndoGaussian
공식 코드EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene Reconstruction
https://github.com/yihui-he/Estimated-Depth-Map-Helps-Image-Classification
공식 코드https://github.com/yilim1/danet
공식 코드https://github.com/yingqianwang/oacc-net
공식 코드Occlusion-Aware Cost Constructor for Light Field Depth Estimation
https://github.com/yjyddq/DLIF
공식 코드https://github.com/youmi-zym/completionformer
공식 코드CompletionFormer: Depth Completion with Convolutions and Vision Transformers
https://github.com/youzunzhi/interpretablemde
공식 코드Towards Interpretable Deep Networks for Monocular Depth Estimation
https://github.com/yshry/libSGM_lidar
공식 코드https://github.com/ysy9997/360Depth
공식 코드Dense Depth Estimation from Multiple 360-degree Images Using Virtual Depth
https://github.com/yt3dvision/4d-mgp-srrnet
공식 코드Rain Removal from Light Field Images with 4D Convolution and Multi-scale Gaussian Process
https://github.com/yuchendoudou/tode
공식 코드TODE-Trans: Transparent Object Depth Estimation with Transformer
https://github.com/yuhuaxu/monostereofusion
공식 코드Depth Estimation by Combining Binocular Stereo and Monocular Structured-Light
https://github.com/yuinsky/gradient-based-depth-map-fusion
공식 코드Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition
https://github.com/yuliangguo/depth_any_camera
공식 코드Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera
https://github.com/yuxinjin-whu/d-dffnet
공식 코드https://github.com/yuyanli0831/omnifusion
공식 코드OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion
https://github.com/yvanyin/filldepth
공식 코드https://github.com/yvanyin/metric3d
공식 코드Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image
https://github.com/yym-sia/lingmi-mr
공식 코드A geometry-aware deep network for depth estimation in monocular endoscopy
https://github.com/yz-wang/demore-net
공식 코드Joint Depth Estimation and Mixture of Rain Removal From a Single Image
https://github.com/yzhao520/CPP
공식 코드Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias
https://github.com/zbw001/tapip3d
공식 코드https://github.com/zcq15/acdnet
공식 코드ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation
https://github.com/zehuichen123/bevdistill
공식 코드BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection
https://github.com/zhangboshen/A2J
공식 코드A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
https://github.com/zhangtaxue/dfr
공식 코드DFR: Depth from Rotation by Uncalibrated Image Rectification with Latitudinal Motion Assumption
https://github.com/zhangyp15/MonoFlex
공식 코드Objects are Different: Flexible Monocular 3D Object Detection
https://github.com/zhaozixiang1228/gdsr-dctnet
공식 코드Discrete Cosine Transform Network for Guided Depth Map Super-Resolution
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.