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.
FSViewFusion: Few-Shots View Generation of Novel Objects
V3D: Video Diffusion Models are Effective 3D Generators
FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization
DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization
Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?
Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving
Finding Waldo: Towards Efficient Exploration of NeRF Scene Spaces
BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling
DART: Implicit Doppler Tomography for Radar Novel View Synthesis
Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views
DaReNeRF: Direction-aware Representation for Dynamic Scenes
Neural Field Classifiers via Target Encoding and Classification Loss
NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning
ViewFusion: Towards Multi-View Consistency via Interpolated Denoising
PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis
AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis
CMC: Few-shot Novel View Synthesis via Cross-view Multiplane Consistency
GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos
TaylorGrid: Towards Fast and High-Quality Implicit Field Learning via Direct Taylor-based Grid Optimization
FrameNeRF: A Simple and Efficient Framework for Few-shot Novel View Synthesis
MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction
Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields
GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering
PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environments
3D Gaussian as a New Era: A Survey
NCRF: Neural Contact Radiance Fields for Free-Viewpoint Rendering of Hand-Object Interaction
SPAD : Spatially Aware Multiview Diffusers
EscherNet: A Generative Model for Scalable View Synthesis
ViewFusion: Learning Composable Diffusion Models for Novel View Synthesis
4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes
Denoising Diffusion via Image-Based Rendering
StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering
360-GS: Layout-guided Panoramic Gaussian Splatting For Indoor Roaming
GaussianStyle: Gaussian Head Avatar via StyleGAN
Advances in 3D Generation: A Survey
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.