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.
$ρ$-NeRF: Leveraging Attenuation Priors in Neural Radiance Field for 3D Computed Tomography Reconstruction
SfM-Free 3D Gaussian Splatting via Hierarchical Training
CRAYM: Neural Field Optimization via Camera RAY Matching
Driving Scene Synthesis on Free-form Trajectories with Generative Prior
HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving
CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion
DynSUP: Dynamic Gaussian Splatting from An Unposed Image Pair
LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes
GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction
DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering
SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
Differentiable Voxel-based X-ray Rendering Improves Sparse-View 3D CBCT Reconstruction
Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting Scenes
AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using Smartphones
SmileSplat: Generalizable Gaussian Splats for Unconstrained Sparse Images
CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model
SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis
Quark: Real-time, High-resolution, and General Neural View Synthesis
MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM
PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence
G2SDF: Surface Reconstruction from Explicit Gaussians with Implicit SDFs
Fixing the Perspective: A Critical Examination of Zero-1-to-3
SplatFlow: Self-Supervised Dynamic Gaussian Splatting in Neural Motion Flow Field for Autonomous Driving
3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
Image Compression Using Novel View Synthesis Priors
Novel View Extrapolation with Video Diffusion Priors
Sparse Input View Synthesis: 3D Representations and Reliable Priors
DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes
Beyond Gaussians: Fast and High-Fidelity 3D Splatting with Linear Kernels
PR-ENDO: Physically Based Relightable Gaussian Splatting for Endoscopy
GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views
SpatialDreamer: Self-supervised Stereo Video Synthesis from Monocular Input
Direct and Explicit 3D Generation from a Single Image
DiHuR: Diffusion-Guided Generalizable Human Reconstruction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.