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.
CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image
StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes
SpatialMe: Stereo Video Conversion Using Depth-Warping and Blend-Inpainting
SweepEvGS: Event-Based 3D Gaussian Splatting for Macro and Micro Radiance Field Rendering from a Single Sweep
PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting
SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video
TSGaussian: Semantic and Depth-Guided Target-Specific Gaussian Splatting from Sparse Views
GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion
unPIC: A Geometric Multiview Prior for Image to 3D Synthesis
DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
Feat2GS: Probing Visual Foundation Models with Gaussian Splatting
PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields
Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Views
EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering
ResGS: Residual Densification of 3D Gaussian for Efficient Detail Recovery
Faster and Better 3D Splatting via Group Training
SimVS: Simulating World Inconsistencies for Robust View Synthesis
From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos
Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video
MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views
MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds
Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis
Pushing Rendering Boundaries: Hard Gaussian Splatting
Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene Reconstruction
Extrapolated Urban View Synthesis Benchmark
HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting
DGNS: Deformable Gaussian Splatting and Dynamic Neural Surface for Monocular Dynamic 3D Reconstruction
Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
Human Multi-View Synthesis from a Single-View Model:Transferred Body and Face Representations
Skel3D: Skeleton Guided Novel View Synthesis
2DGS-Room: Seed-Guided 2D Gaussian Splatting with Geometric Constrains for High-Fidelity Indoor Scene Reconstruction
NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images
Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.