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.
Revising Densification in Gaussian Splatting
Gaussian Pancakes: Geometrically-Regularized 3D Gaussian Splatting for Realistic Endoscopic Reconstruction
HFNeRF: Learning Human Biomechanic Features with Neural Radiance Fields
Learning Topology Uniformed Face Mesh by Volume Rendering for Multi-view Reconstruction
CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis
Z-Splat: Z-Axis Gaussian Splatting for Camera-Sonar Fusion
GaSpCT: Gaussian Splatting for Novel CT Projection View Synthesis
Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting
The More You See in 2D, the More You Perceive in 3D
RaFE: Generative Radiance Fields Restoration
LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis
Many-to-many Image Generation with Auto-regressive Diffusion Models
GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views
NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation
SGCNeRF: Few-Shot Neural Rendering via Sparse Geometric Consistency Guidance
CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians
Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splatting
SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering
Knowledge NeRF: Few-shot Novel View Synthesis for Dynamic Articulated Objects
Stable Surface Regularization for Fast Few-Shot NeRF
Grounding and Enhancing Grid-based Models for Neural Fields
NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising
SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior
Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds
CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians
XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold
SAID-NeRF: Segmentation-AIDed NeRF for Depth Completion of Transparent Objects
GauStudio: A Modular Framework for 3D Gaussian Splatting and Beyond
Mitigating Motion Blur in Neural Radiance Fields with Events and Frames
Modeling uncertainty for Gaussian Splatting
SplatFace: Gaussian Splat Face Reconstruction Leveraging an Optimizable Surface
MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering
NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation
Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.