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.
Gaussian Heritage: 3D Digitization of Cultural Heritage with Integrated Object Segmentation
Disentangled Generation and Aggregation for Robust Radiance Fields
Semantics-Controlled Gaussian Splatting for Outdoor Scene Reconstruction and Rendering in Virtual Reality
GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization
AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark
FusionRF: High-Fidelity Satellite Neural Radiance Fields from Multispectral and Panchromatic Acquisitions
SpikeGS: Learning 3D Gaussian Fields from Continuous Spike Stream
MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views
Spectral-GS: Taming 3D Gaussian Splatting with Spectral Entropy
GaRField++: Reinforced Gaussian Radiance Fields for Large-Scale 3D Scene Reconstruction
GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling
GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations
LEMON: Localized Editing with Mesh Optimization and Neural Shaders
Single-Layer Learnable Activation for Implicit Neural Representation (SL$^{2}$A-INR)
MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation
CSS: Overcoming Pose and Scene Challenges in Crowd-Sourced 3D Gaussian Splatting
Dense Point Clouds Matter: Dust-GS for Scene Reconstruction from Sparse Viewpoints
Thermal3D-GS: Physics-induced 3D Gaussians for Thermal Infrared Novel-view Synthesis
VI3DRM:Towards meticulous 3D Reconstruction from Sparse Views via Photo-Realistic Novel View Synthesis
Diversity-Driven View Subset Selection for Indoor Novel View Synthesis
MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis
Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models
GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction
G-NeLF: Memory- and Data-Efficient Hybrid Neural Light Field for Novel View Synthesis
CD-NGP: A Fast Scalable Continual Representation for Dynamic Scenes
Fisheye-GS: Lightweight and Extensible Gaussian Splatting Module for Fisheye Cameras
Optimizing 3D Gaussian Splatting for Sparse Viewpoint Scene Reconstruction
View-Invariant Policy Learning via Zero-Shot Novel View Synthesis
UC-NeRF: Uncertainty-aware Conditional Neural Radiance Fields from Endoscopic Sparse Views
$S^2$NeRF: Privacy-preserving Training Framework for NeRF
ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
Spurfies: Sparse Surface Reconstruction using Local Geometry Priors
Generic Objects as Pose Probes for Few-shot View Synthesis
GameIR: A Large-Scale Synthesized Ground-Truth Dataset for Image Restoration over Gaming Content
G-Style: Stylized Gaussian Splatting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.