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.
SMORE: Simultaneous Map and Object REconstruction
HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
MegaScenes: Scene-Level View Synthesis at Scale
A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets
DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features
RaNeuS: Ray-adaptive Neural Surface Reconstruction
D-NPC: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Video
GaussianSR: 3D Gaussian Super-Resolution with 2D Diffusion Priors
PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting
Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections
GaussianForest: Hierarchical-Hybrid 3D Gaussian Splatting for Compressed Scene Modeling
Modeling Ambient Scene Dynamics for Free-view Synthesis
Spatial Annealing for Efficient Few-shot Neural Rendering
From Chaos to Clarity: 3DGS in the Dark
Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field
Generalizable Human Gaussians from Single-View Image
Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis
VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
RefGaussian: Disentangling Reflections from 3D Gaussian Splatting for Realistic Rendering
Multi-style Neural Radiance Field with AdaIN
Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling
Encoding Semantic Priors into the Weights of Implicit Neural Representation
Conv-INR: Convolutional Implicit Neural Representation for Multimodal Visual Signals
Coarse-To-Fine Tensor Trains for Compact Visual Representations
Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image
Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion
Dynamic 3D Gaussian Fields for Urban Areas
WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections
Self-Calibrating 4D Novel View Synthesis from Monocular Videos Using Gaussian Splatting
RaDe-GS: Rasterizing Depth in Gaussian Splatting
Learning Temporally Consistent Video Depth from Video Diffusion Priors
Efficient Neural Light Fields (ENeLF) for Mobile Devices
Bilateral Guided Radiance Field Processing
ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Model
GS-Phong: Meta-Learned 3D Gaussians for Relightable Novel View Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.