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 Mapping for Evolving Scenes
SurGSplat: Progressive Geometry-Constrained Gaussian Splatting for Surgical Scene Reconstruction
Splat and Replace: 3D Reconstruction with Repetitive Elements
Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations
UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splatting
RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion
ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimation
Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting
On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset
RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS
PhysGaia: A Physics-Aware Dataset of Multi-Body Interactions for Dynamic Novel View Synthesis
Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
Radiant Triangle Soup with Soft Connectivity Forces for 3D Reconstruction and Novel View Synthesis
Mobi-$π$: Mobilizing Your Robot Learning Policy
AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
Test-Time Training Done Right
3DGEER: Exact and Efficient Volumetric Rendering with 3D Gaussians
3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling
Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction
GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis
Sparse2DGS: Sparse-View Surface Reconstruction using 2D Gaussian Splatting with Dense Point Cloud
ErpGS: Equirectangular Image Rendering enhanced with 3D Gaussian Regularization
Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency
Veta-GS: View-dependent deformable 3D Gaussian Splatting for thermal infrared Novel-view Synthesis
Triangle Splatting for Real-Time Radiance Field Rendering
Improving Novel view synthesis of 360$^\circ$ Scenes in Extremely Sparse Views by Jointly Training Hemisphere Sampled Synthetic Images
SuperGS: Consistent and Detailed 3D Super-Resolution Scene Reconstruction via Gaussian Splatting
SpikeGen: Generative Framework for Visual Spike Stream Processing
CTRL-GS: Cascaded Temporal Residue Learning for 4D Gaussian Splatting
RealEngine: Simulating Autonomous Driving in Realistic Context
Continuous Representation Methods, Theories, and Applications: An Overview and Perspectives
MGStream: Motion-aware 3D Gaussian for Streamable Dynamic Scene Reconstruction
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.