Papers with Code 아카이브
Depth Completion
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 9
- 보존된 평가 기록
- 32
The Depth Completion task is a sub-problem of depth estimation. In the sparse-to-dense depth completion problem, one wants to infer the dense depth map of a 3-D scene given an RGB image and its corresponding sparse reconstruction in the form of a sparse depth map obtained either from computational methods such as SfM (Strcuture-from-Motion) or active sensors such as lidar or structured light sensors.
Source: LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery , Unsupervised Depth Completion from Visual Inertial Odometry
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
DidSee: Diffusion-Based Depth Completion for Material-Agnostic Robotic Perception and Manipulation
DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects
SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completion
BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World
Event-Driven Dynamic Scene Depth Completion
Depth Anything with Any Prior
WonderTurbo: Generating Interactive 3D World in 0.72 Seconds
All-day Depth Completion via Thermal-LiDAR Fusion
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image
DenseFormer: Learning Dense Depth Map from Sparse Depth and Image via Conditional Diffusion Model
Vanishing Depth: A Depth Adapter with Positional Depth Encoding for Generalized Image Encoders
GAA-TSO: Geometry-Aware Assisted Depth Completion for Transparent and Specular Objects
Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors
ProtoDepth: Unsupervised Continual Depth Completion with Prototypes
SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
Learning Inverse Laplacian Pyramid for Progressive Depth Completion
TranSplat: Surface Embedding-guided 3D Gaussian Splatting for Transparent Object Manipulation
GAC-Net_Geometric and attention-based Network for Depth Completion
Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion
DepthLab: From Partial to Complete
TDCNet: Transparent Objects Depth Completion with CNN-Transformer Dual-Branch Parallel Network
Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion
OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration
Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation
CFPNet: Improving Lightweight ToF Depth Completion via Cross-zone Feature Propagation
Scale Propagation Network for Generalizable Depth Completion
UnCLe: Unsupervised Continual Learning of Depth Completion
Deep Cost Ray Fusion for Sparse Depth Video Completion
Optical Flow Matters: an Empirical Comparative Study on Fusing Monocular Extracted Modalities for Better Steering
SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps
SDformer: Efficient End-to-End Transformer for Depth Completion
DistillGrasp: Integrating Features Correlation with Knowledge Distillation for Depth Completion of Transparent Objects
SMORE: Simultaneous Map and Object REconstruction
Temporal Lidar Depth Completion
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.