Papers with Code 아카이브
Novel View Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 24
- 보존된 평가 기록
- 103
Synthesize a target image with an arbitrary target camera pose from given source images and their camera poses.
See Wiki for more introductions.
The Synthesis method include: NeRF, MPI and so on.
<span style="color:grey; opacity: 0.6">( Image credit: Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations
Exploiting Radiance Fields for Grasp Generation on Novel Synthetic Views
VRSplat: Fast and Robust Gaussian Splatting for Virtual Reality
NVSPolicy: Adaptive Novel-View Synthesis for Generalizable Language-Conditioned Policy Learning
Consistent Quantity-Quality Control across Scenes for Deployment-Aware Gaussian Splatting
Geometric Prior-Guided Neural Implicit Surface Reconstruction in the Wild
TUM2TWIN: Introducing the Large-Scale Multimodal Urban Digital Twin Benchmark Dataset
NeuGen: Amplifying the 'Neural' in Neural Radiance Fields for Domain Generalization
RefRef: A Synthetic Dataset and Benchmark for Reconstructing Refractive and Reflective Objects
Steepest Descent Density Control for Compact 3D Gaussian Splatting
SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting
High Dynamic Range Novel View Synthesis with Single Exposure
RayZer: A Self-supervised Large View Synthesis Model
GaussTrap: Stealthy Poisoning Attacks on 3D Gaussian Splatting for Targeted Scene Confusion
TesserAct: Learning 4D Embodied World Models
Unconstrained Large-scale 3D Reconstruction and Rendering across Altitudes
CE-NPBG: Connectivity Enhanced Neural Point-Based Graphics for Novel View Synthesis in Autonomous Driving Scenes
TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians
CasualHDRSplat: Robust High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos
iVR-GS: Inverse Volume Rendering for Explorable Visualization via Editable 3D Gaussian Splatting
HUG: Hierarchical Urban Gaussian Splatting with Block-Based Reconstruction for Large-Scale Aerial Scenes
Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning
MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video
Metamon-GS: Enhancing Representability with Variance-Guided Densification and Light Encoding
VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control
IXGS-Intraoperative 3D Reconstruction from Sparse, Arbitrarily Posed Real X-rays
SLAM&Render: A Benchmark for the Intersection Between Neural Rendering, Gaussian Splatting and SLAM
Second-order Optimization of Gaussian Splats with Importance Sampling
AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos
EBAD-Gaussian: Event-driven Bundle Adjusted Deblur Gaussian Splatting
LL-Gaussian: Low-Light Scene Reconstruction and Enhancement via Gaussian Splatting for Novel View Synthesis
BlockGaussian: Efficient Large-Scale Scene Novel View Synthesis via Adaptive Block-Based Gaussian Splatting
Geometric Consistency Refinement for Single Image Novel View Synthesis via Test-Time Adaptation of Diffusion Models
SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.