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.
Enhancing 3D Gaussian Splatting Compression via Spatial Condition-based Prediction
Disentangled 4D Gaussian Splatting: Towards Faster and More Efficient Dynamic Scene Rendering
GenFusion: Closing the Loop between Reconstruction and Generation via Videos
Frequency-Aware Gaussian Splatting Decomposition
RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting
EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis
TC-GS: Tri-plane based compression for 3D Gaussian Splatting
HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting
CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis
MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction
StableGS: A Floater-Free Framework for 3D Gaussian Splatting
Hardware-Rasterized Ray-Based Gaussian Splatting
Accenture-NVS1: A Novel View Synthesis Dataset
NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting
ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes
Enhancing Close-up Novel View Synthesis via Pseudo-labeling
Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation
Learn Your Scales: Towards Scale-Consistent Generative Novel View Synthesis
CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image
Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes
Light4GS: Lightweight Compact 4D Gaussian Splatting Generation via Context Model
Lightweight Gradient-Aware Upscaling of 3D Gaussian Splatting Images
RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images
Segmentation-Guided Neural Radiance Fields for Novel Street View Synthesis
Improving Adaptive Density Control for 3D Gaussian Splatting
Optimized 3D Gaussian Splatting using Coarse-to-Fine Image Frequency Modulation
CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting
AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction
DivCon-NeRF: Generating Augmented Rays with Diversity and Consistency for Few-shot View Synthesis
Next-Scale Autoregressive Models are Zero-Shot Single-Image Object View Synthesizers
Improving Geometric Consistency for 360-Degree Neural Radiance Fields in Indoor Scenarios
GS-I$^{3}$: Gaussian Splatting for Surface Reconstruction from Illumination-Inconsistent Images
MTGS: Multi-Traversal Gaussian Splatting
Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.