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.
The Oxford Spires Dataset: Benchmarking Large-Scale LiDAR-Visual Localisation, Reconstruction and Radiance Field Methods
SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction
Mono2Stereo: Monocular Knowledge Transfer for Enhanced Stereo Matching
DyGASR: Dynamic Generalized Exponential Splatting with Surface Alignment for Accelerated 3D Mesh Reconstruction
BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis
4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization
Projecting Gaussian Ellipsoids While Avoiding Affine Projection Approximation
Novel View Synthesis with Pixel-Space Diffusion Models
A Hierarchical Compression Technique for 3D Gaussian Splatting Compression
Through the Curved Cover: Synthesizing Cover Aberrated Scenes with Refractive Field
SplatFormer: Point Transformer for Robust 3D Gaussian Splatting
Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction
GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting
GANESH: Generalizable NeRF for Lensless Imaging
MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis
FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video
CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes
GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering
No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis
Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis
PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting
GUMBEL-NERF: Representing Unseen Objects as Part-Compositional Neural Radiance Fields
Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering
ArCSEM: Artistic Colorization of SEM Images via Gaussian Splatting
Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction
Few-shot NeRF by Adaptive Rendering Loss Regularization
VR-Splatting: Foveated Radiance Field Rendering via 3D Gaussian Splatting and Neural Points
FreeVS: Generative View Synthesis on Free Driving Trajectory
VistaDream: Sampling multiview consistent images for single-view scene reconstruction
LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias
Fully Explicit Dynamic Gaussian Splatting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.