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.
MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement
Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
Deep Learning at the Intersection: Certified Robustness as a Tool for 3D Vision
BiGS: Bidirectional Gaussian Primitives for Relightable 3D Gaussian Splatting
SpecGaussian with Latent Features: A High-quality Modeling of the View-dependent Appearance for 3D Gaussian Splatting
Subsurface Scattering for 3D Gaussian Splatting
Pano2Room: Novel View Synthesis from a Single Indoor Panorama
Robust 3D Gaussian Splatting for Novel View Synthesis in Presence of Distractors
TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks
Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representation
GS-ID: Illumination Decomposition on Gaussian Splatting via Diffusion Prior and Parametric Light Source Optimization
Correspondence-Guided SfM-Free 3D Gaussian Splatting for NVS
MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing
Rethinking Open-Vocabulary Segmentation of Radiance Fields in 3D Space
Progressive Radiance Distillation for Inverse Rendering with Gaussian Splatting
ActiveNeRF: Learning Accurate 3D Geometry by Active Pattern Projection
SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields
NeRF-US: Removing Ultrasound Imaging Artifacts from Neural Radiance Fields in the Wild
3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance
Mipmap-GS: Let Gaussians Deform with Scale-specific Mipmap for Anti-aliasing Rendering
PRTGaussian: Efficient Relighting Using 3D Gaussians with Precomputed Radiance Transfer
Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis
FewShotNeRF: Meta-Learning-based Novel View Synthesis for Rapid Scene-Specific Adaptation
3iGS: Factorised Tensorial Illumination for 3D Gaussian Splatting
MGFs: Masked Gaussian Fields for Meshing Building based on Multi-View Images
RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis
LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splatting
Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation
Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering
IOVS4NeRF:Incremental Optimal View Selection for Large-Scale NeRFs
Towards the Spectral bias Alleviation by Normalizations in Coordinate Networks
Pose Estimation from Camera Images for Underwater Inspection
SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency
HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction from Raw Images
DHGS: Decoupled Hybrid Gaussian Splatting for Driving Scene
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.