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.
Amodal Depth Anything: Amodal Depth Estimation in the Wild
Dual Exposure Stereo for Extended Dynamic Range 3D Imaging
Single-Shot Metric Depth from Focused Plenoptic Cameras
STATIC : Surface Temporal Affine for TIme Consistency in Video Monocular Depth Estimation
HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving
AVS-Net: Audio-Visual Scale Net for Self-supervised Monocular Metric Depth Estimation
Mutli-View 3D Reconstruction using Knowledge Distillation
FiffDepth: Feed-forward Transformation of Diffusion-Based Generators for Detailed Depth Estimation
Gaussian Splashing: Direct Volumetric Rendering Underwater
MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applications
SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection
360Recon: An Accurate Reconstruction Method Based on Depth Fusion from 360 Images
Video Depth without Video Models
SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation
GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation
Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation
Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration
DepthCues: Evaluating Monocular Depth Perception in Large Vision Models
Spatially Visual Perception for End-to-End Robotic Learning
DROID-Splat: Combining end-to-end SLAM with 3D Gaussian Splatting
Low-rank Adaptation-based All-Weather Removal for Autonomous Navigation
One Diffusion to Generate Them All
Generative Omnimatte: Learning to Decompose Video into Layers
Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
PriorDiffusion: Leverage Language Prior in Diffusion Models for Monocular Depth Estimation
OceanLens: An Adaptive Backscatter and Edge Correction using Deep Learning Model for Enhanced Underwater Imaging
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
Scalable Autoregressive Monocular Depth Estimation
GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views
The ADUULM-360 Dataset -- A Multi-Modal Dataset for Depth Estimation in Adverse Weather
MGNiceNet: Unified Monocular Geometric Scene Understanding
MetricGold: Leveraging Text-To-Image Latent Diffusion Models for Metric Depth Estimation
Efficient Depth Estimation for Unstable Stereo Camera Systems on AR Glasses
SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction
Mono2Stereo: Monocular Knowledge Transfer for Enhanced Stereo Matching
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.