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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Depth Estimation using Weighted-loss and Transfer Learning
Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation
MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views
MoCha-Stereo: Motif Channel Attention Network for Stereo Matching
Self-supervised Monocular Depth Estimation on Water Scenes via Specular Reflection Prior
Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes
Enhanced Radar Perception via Multi-Task Learning: Towards Refined Data for Sensor Fusion Applications
Unified Physical-Digital Attack Detection Challenge
RoadBEV: Road Surface Reconstruction in Bird's Eye View
HawkDrive: A Transformer-driven Visual Perception System for Autonomous Driving in Night Scene
Deep Phase Coded Image Prior
MonoCD: Monocular 3D Object Detection with Complementary Depths
Adaptive Discrete Disparity Volume for Self-supervised Monocular Depth Estimation
WorDepth: Variational Language Prior for Monocular Depth Estimation
MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning
Improving Bird's Eye View Semantic Segmentation by Task Decomposition
CHOSEN: Contrastive Hypothesis Selection for Multi-View Depth Refinement
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
Flare-Free Vision: Empowering Uformer with Depth Insights
MaGRITTe: Manipulative and Generative 3D Realization from Image, Topview and Text
NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising
VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection
FlowDepth: Decoupling Optical Flow for Self-Supervised Monocular Depth Estimation
Test-Time Domain Generalization for Face Anti-Spoofing
SAID-NeRF: Segmentation-AIDed NeRF for Depth Completion of Transparent Objects
$\mathrm{F^2Depth}$: Self-supervised Indoor Monocular Depth Estimation via Optical Flow Consistency and Feature Map Synthesis
ModaLink: Unifying Modalities for Efficient Image-to-PointCloud Place Recognition
ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation
UniDepth: Universal Monocular Metric Depth Estimation
Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing
Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos
Track Everything Everywhere Fast and Robustly
Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.