Papers with Code 아카이브
3D Scene Reconstruction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
Creating 3D scene either using conventional SFM pipelines or latest deep learning approaches.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting
NexusSplats: Efficient 3D Gaussian Splatting in the Wild
Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Survey
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
Sort-free Gaussian Splatting via Weighted Sum Rendering
FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors
Ego3DT: Tracking Every 3D Object in Ego-centric Videos
G3R: Gradient Guided Generalizable Reconstruction
Neural Implicit Representation for Highly Dynamic LiDAR Mapping and Odometry
Go-SLAM: Grounded Object Segmentation and Localization with Gaussian Splatting SLAM
GaRField++: Reinforced Gaussian Radiance Fields for Large-Scale 3D Scene Reconstruction
Sources of Uncertainty in 3D Scene Reconstruction
Online 3D reconstruction and dense tracking in endoscopic videos
EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping System
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction
WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting
Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methods
FBINeRF: Feature-Based Integrated Recurrent Network for Pinhole and Fisheye Neural Radiance Fields
HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction from Raw Images
Monocular Occupancy Prediction for Scalable Indoor Scenes
Evaluating geometric accuracy of NeRF reconstructions compared to SLAM method
Survey on Fundamental Deep Learning 3D Reconstruction Techniques
WildGaussians: 3D Gaussian Splatting in the Wild
SpikeGS: Reconstruct 3D scene via fast-moving bio-inspired sensors
CRiM-GS: Continuous Rigid Motion-Aware Gaussian Splatting from Motion-Blurred Images
DoubleTake: Geometry Guided Depth Estimation
OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained Understanding
PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Driving
Object-level Scene Deocclusion
RefGaussian: Disentangling Reflections from 3D Gaussian Splatting for Realistic Rendering
CMAR-Net: Accurate Cross-Modal 3D SAR Reconstruction of Vehicle Targets with Sparse-Aspect Multi-Baseline Data
Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image
Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion
3D-HGS: 3D Half-Gaussian Splatting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.