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.
CheapNVS: Real-Time On-Device Narrow-Baseline Novel View Synthesis
GoDe: Gaussians on Demand for Progressive Level of Detail and Scalable Compression
DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform
GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting
3DGS$^2$: Near Second-order Converging 3D Gaussian Splatting
Survey on Monocular Metric Depth Estimation
HAC++: Towards 100X Compression of 3D Gaussian Splatting
See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization
Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting
CrossModalityDiffusion: Multi-Modal Novel View Synthesis with Unified Intermediate Representation
VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenes
3D Gaussian Splatting with Normal Information for Mesh Extraction and Improved Rendering
Evaluating Human Perception of Novel View Synthesis: Subjective Quality Assessment of Gaussian Splatting and NeRF in Dynamic Scenes
Aug3D: Augmenting large scale outdoor datasets for Generalizable Novel View Synthesis
MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesis
Scaffold-SLAM: Structured 3D Gaussians for Simultaneous Localization and Photorealistic Mapping
FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency
DehazeGS: Seeing Through Fog with 3D Gaussian Splatting
NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives
Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis
GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking
CrossView-GS: Cross-view Gaussian Splatting For Large-scale Scene Reconstruction
EasySplat: View-Adaptive Learning makes 3D Gaussian Splatting Easy
SG-Splatting: Accelerating 3D Gaussian Splatting with Spherical Gaussians
SoundBrush: Sound as a Brush for Visual Scene Editing
4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives
KeyGS: A Keyframe-Centric Gaussian Splatting Method for Monocular Image Sequences
MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks
DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
Learning Radiance Fields from a Single Snapshot Compressive Image
Dust to Tower: Coarse-to-Fine Photo-Realistic Scene Reconstruction from Sparse Uncalibrated Images
Reflective Gaussian Splatting
BeSplat: Gaussian Splatting from a Single Blurry Image and Event Stream
GSAVS: Gaussian Splatting-based Autonomous Vehicle Simulator
RSGaussian:3D Gaussian Splatting with LiDAR for Aerial Remote Sensing Novel View Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.