https://github.com/silvialaurapintea/reg-cls
공식 코드A step towards understanding why classification helps regression
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/simondemoreau/led
공식 코드https://github.com/sjg02122/MonoFormer
공식 코드Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation
https://github.com/sjingjia/planerectr
공식 코드PlaneRecTR++: Unified Query Learning for Joint 3D Planar Reconstruction and Pose Estimation
https://github.com/sjtu-visys/sdg-depth
공식 코드Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion
https://github.com/sjtu-visys/structdepth
공식 코드StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation
https://github.com/skmhrk1209/VSRD
공식 코드VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection
https://github.com/sleekeagle/defocus_camind
공식 코드Camera-Independent Single Image Depth Estimation from Defocus Blur
https://github.com/smartbot-pjlab/dort
공식 코드DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking
https://github.com/sniklaus/3d-ken-burns
공식 코드https://github.com/sniklaus/softmax-splatting
공식 코드https://github.com/snldmt/SPARS3R
공식 코드SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction
https://github.com/sony/genwarp
공식 코드GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping
https://github.com/spengliang/did-m3d
공식 코드DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection
https://github.com/sshan-zhao/GASDA
공식 코드Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation
https://github.com/stac-usc/color_guided_flying_pixel_correction_in_depth_images
공식 코드https://github.com/sty61010/crossdtr
공식 코드CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection
https://github.com/sum1lim/PU-Ray
공식 코드PU-Ray: Domain-Independent Point Cloud Upsampling via Ray Marching on Neural Implicit Surface
https://github.com/sungmin-woo/ProDepth
공식 코드ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
https://github.com/sunh18/monosim
공식 코드https://github.com/sunnyhelen/jperceiver
공식 코드JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes
https://github.com/sunnyhelen/rcvc-depth
공식 코드On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation
https://github.com/sunpihai-up/fuse
공식 코드https://github.com/sunset1995/HoHoNet
공식 코드HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features
https://github.com/sunyiyou/safas
공식 코드Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment
https://github.com/supermhp/gupnet
공식 코드Geometry Uncertainty Projection Network for Monocular 3D Object Detection
https://github.com/susaha/ctrl-uda
공식 코드Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
https://github.com/svip-lab/FastMVSNet
공식 코드Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement
https://github.com/svip-lab/Indoor-SfMLearner
공식 코드P$^{2}$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
https://github.com/svip-lab/planedepth
공식 코드PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes
https://github.com/swintransformer/ait
공식 코드All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
https://github.com/syscv/p3depth
공식 코드P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior
https://github.com/syy-whu/semi-moregan
공식 코드Semi-MoreGAN: A New Semi-supervised Generative Adversarial Network for Mixture of Rain Removal
https://github.com/tai-wang/depth-from-motion
공식 코드https://github.com/taylover-pei/SSDG-CVPR2020
공식 코드https://github.com/tb2-sy/tsp-transformer
공식 코드TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.