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.
MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second
Cameras as Relative Positional Encoding
Reflections Unlock: Geometry-Aware Reflection Disentanglement in 3D Gaussian Splatting for Photorealistic Scenes Rendering
LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures
Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps
Refine Any Object in Any Scene
VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding
UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields
DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting
User-in-the-Loop View Sampling with Error Peaking Visualization
Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Image
EndoFlow-SLAM: Real-Time Endoscopic SLAM with Flow-Constrained Gaussian Splatting
DreamAnywhere: Object-Centric Panoramic 3D Scene Generation
Virtual Memory for 3D Gaussian Splatting
Self-Supervised Multimodal NeRF for Autonomous Driving
BulletGen: Improving 4D Reconstruction with Bullet-Time Generation
R3eVision: A Survey on Robust Rendering, Restoration, and Enhancement for 3D Low-Level Vision
HRGS: Hierarchical Gaussian Splatting for Memory-Efficient High-Resolution 3D Reconstruction
3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting
WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild
TextureSplat: Per-Primitive Texture Mapping for Reflective Gaussian Splatting
Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry
Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors
CGVQM+D: Computer Graphics Video Quality Metric and Dataset
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
VEIGAR: View-consistent Explicit Inpainting and Geometry Alignment for 3D object Removal
SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis
Anti-Aliased 2D Gaussian Splatting
UniForward: Unified 3D Scene and Semantic Field Reconstruction via Feed-Forward Gaussian Splatting from Only Sparse-View Images
The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images without Any 3D Knowledge
TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering
Princeton365: A Diverse Dataset with Accurate Camera Pose
Hierarchical Scoring with 3D Gaussian Splatting for Instance Image-Goal Navigation
OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting
Speedy Deformable 3D Gaussian Splatting: Fast Rendering and Compression of Dynamic Scenes
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.