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.
GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
Morpheus: Text-Driven 3D Gaussian Splat Shape and Color Stylization
PSRGS:Progressive Spectral Residual of 3D Gaussian for High-Frequency Recovery
Seeing A 3D World in A Grain of Sand
No Parameters, No Problem: 3D Gaussian Splatting without Camera Intrinsics and Extrinsics
Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?
Synthesizing Consistent Novel Views via 3D Epipolar Attention without Re-Training
Efficient 4D Gaussian Stream with Low Rank Adaptation
RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes
Para-Lane: Multi-Lane Dataset Registering Parallel Scans for Benchmarking Novel View Synthesis
Exploiting Deblurring Networks for Radiance Fields
CDGS: Confidence-Aware Depth Regularization for 3D Gaussian Splatting
RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation
Betsu-Betsu: Multi-View Separable 3D Reconstruction of Two Interacting Objects
Inter3D: A Benchmark and Strong Baseline for Human-Interactive 3D Object Reconstruction
HumanGif: Single-View Human Diffusion with Generative Prior
FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views
OMG: Opacity Matters in Material Modeling with Gaussian Splatting
E-3DGS: Event-Based Novel View Rendering of Large-Scale Scenes Using 3D Gaussian Splatting
Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting
Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors
Matrix3D: Large Photogrammetry Model All-in-One
SIREN: Semantic, Initialization-Free Registration of Multi-Robot Gaussian Splatting Maps
GAS: Generative Avatar Synthesis from a Single Image
PoI: Pixel of Interest for Novel View Synthesis Assisted Scene Coordinate Regression
VistaFlow: Photorealistic Volumetric Reconstruction with Dynamic Resolution Management via Q-Learning
GP-GS: Gaussian Processes for Enhanced Gaussian Splatting
Geometric Neural Process Fields
WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction
Advancing Dense Endoscopic Reconstruction with Gaussian Splatting-driven Surface Normal-aware Tracking and Mapping
Lifting by Gaussians: A Simple, Fast and Flexible Method for 3D Instance Segmentation
Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion
LinPrim: Linear Primitives for Differentiable Volumetric Rendering
Deformable Beta Splatting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.