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.
PNeRFLoc: Visual Localization with Point-based Neural Radiance Fields
TIFace: Improving Facial Reconstruction through Tensorial Radiance Fields and Implicit Surfaces
SLS4D: Sparse Latent Space for 4D Novel View Synthesis
RANRAC: Robust Neural Scene Representations via Random Ray Consensus
SlimmeRF: Slimmable Radiance Fields
CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning
VaLID: Variable-Length Input Diffusion for Novel View Synthesis
ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field
Novel View Synthesis with View-Dependent Effects from a Single Image
Neural Radiance Fields for Transparent Object Using Visual Hull
Global Latent Neural Rendering
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
NViST: In the Wild New View Synthesis from a Single Image with Transformers
Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs
NVS-Adapter: Plug-and-Play Novel View Synthesis from a Single Image
COLMAP-Free 3D Gaussian Splatting
SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration
NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos
CorresNeRF: Image Correspondence Priors for Neural Radiance Fields
Learning Naturally Aggregated Appearance for Efficient 3D Editing
UpFusion: Novel View Diffusion from Unposed Sparse View Observations
Gaussian Splatting SLAM
NeVRF: Neural Video-based Radiance Fields for Long-duration Sequences
MuVieCAST: Multi-View Consistent Artistic Style Transfer
GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization
Towards 4D Human Video Stylization
Multi-View Unsupervised Image Generation with Cross Attention Guidance
Free3D: Consistent Novel View Synthesis without 3D Representation
Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
Artist-Friendly Relightable and Animatable Neural Heads
DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
GauHuman: Articulated Gaussian Splatting from Monocular Human Videos
ReconFusion: 3D Reconstruction with Diffusion Priors
GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation
ColonNeRF: High-Fidelity Neural Reconstruction of Long Colonoscopy
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.