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.
Harnessing Diffusion Models for Visual Perception with Meta Prompts
Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformers
DUSt3R: Geometric 3D Vision Made Easy
PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation
Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model
NeRF-VO: Real-Time Sparse Visual Odometry with Neural Radiance Fields
Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion
DDOS: The Drone Depth and Obstacle Segmentation Dataset
Long-Tailed 3D Detection via Multi-Modal Fusion
From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior
CT-MVSNet: Efficient Multi-View Stereo with Cross-scale Transformer
Guided Image Restoration via Simultaneous Feature and Image Guided Fusion
ReCoRe: Regularized Contrastive Representation Learning of World Model
Text2Immersion: Generative Immersive Scene with 3D Gaussians
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments
ArcGAN: Generative Adversarial Networks for 3D Architectural Image Generation
Instance-aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment
Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops
Camera-based 3D Semantic Scene Completion with Sparse Guidance Network
SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolution
GenDepth: Generalizing Monocular Depth Estimation for Arbitrary Camera Parameters via Ground Plane Embedding
Fine Dense Alignment of Image Bursts through Camera Pose and Depth Estimation
Camera Height Doesn't Change: Unsupervised Training for Metric Monocular Road-Scene Depth Estimation
Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI
Artificial Neural Network for Estimation of Physical Parameters of Sea Water using LiDAR Waveforms
BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection
GIVT: Generative Infinite-Vocabulary Transformers
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation
Deeper into Self-Supervised Monocular Indoor Depth Estimation
Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D
Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion
Enhancing Diffusion Models with 3D Perspective Geometry Constraints
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.