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>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/nvlabs/svraster

공식 코드

Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

https://github.com/nvlabs/tiny-cuda-nn

공식 코드

Instant Neural Graphics Primitives with a Multiresolution Hash Encoding

https://github.com/ohsngjun/3D-4DGS

공식 코드

Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation

https://github.com/oppo-us-research/relitneulf

공식 코드

Relit-NeuLF: Efficient Relighting and Novel View Synthesis via Neural 4D Light Field

https://github.com/oppo-us-research/spacetimegaussians

공식 코드

Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis

https://github.com/paoyw/Stylized-NeRF-with-AdaIN

공식 코드

Multi-style Neural Radiance Field with AdaIN

https://github.com/paulungermann/Robust3DGaussians

공식 코드

Robust 3D Gaussian Splatting for Novel View Synthesis in Presence of Distractors

https://github.com/pcl3dv/dunerf

공식 코드

3D Reconstruction and New View Synthesis of Indoor Environments based on a Dual Neural Radiance Field

https://github.com/pcl3dv/mgstream

공식 코드

MGStream: Motion-aware 3D Gaussian for Streamable Dynamic Scene Reconstruction

https://github.com/perf-project/PeRF

공식 코드

PERF: Panoramic Neural Radiance Field from a Single Panorama

https://github.com/pjlab-ADG/neuralsim

공식 코드

StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views

https://github.com/polysummit/raise

공식 코드

Refine Any Object in Any Scene

https://github.com/prinasi/mono-hdr-3d

공식 코드

High Dynamic Range Novel View Synthesis with Single Exposure

https://github.com/pris-cv/humanrecon

공식 코드

HumanRecon: Neural Reconstruction of Dynamic Human Using Geometric Cues and Physical Priors

https://github.com/prstrive/scgaussian

공식 코드

Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis

https://github.com/pulangk97/SANeRF

공식 코드

Spatial Annealing for Efficient Few-shot Neural Rendering

https://github.com/pzzz-cv/RStab

공식 코드

3D Multi-frame Fusion for Video Stabilization

https://github.com/qianmingduowan/Sat2Density

공식 코드

Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs

https://github.com/qianyiwu/objsdf

공식 코드

Object-Compositional Neural Implicit Surfaces

https://github.com/qihanggh/imrc

공식 코드

Evaluate Geometry of Radiance Fields with Low-frequency Color Prior

https://github.com/qt-zhu/rpbg

공식 코드

RPBG: Towards Robust Neural Point-based Graphics in the Wild

https://github.com/quan-meng/gnerf

공식 코드

GNeRF: GAN-based Neural Radiance Field without Posed Camera

https://github.com/r4dl/stopthepop

공식 코드

StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering

https://github.com/raja-kumar/depth-aware-3dgs

공식 코드

Few-shot Novel View Synthesis using Depth Aware 3D Gaussian Splatting

https://github.com/rakhimovv/npbgpp

공식 코드

NPBG++: Accelerating Neural Point-Based Graphics

https://github.com/rando11199/triplet

공식 코드

Triplet: Triangle Patchlet for Mesh-Based Inverse Rendering and Scene Parameters Approximation

https://github.com/raymondwang987/nvds

공식 코드

NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation

https://github.com/realcrane/student-splating-scooping

공식 코드

3D Student Splatting and Scooping

https://github.com/redrock303/NeRFLiX_CPVR2023

공식 코드

NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer

https://github.com/rehg-lab/dope_selfsup

공식 코드

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization

https://github.com/renaissanceee/mipmap-gs

공식 코드

Mipmap-GS: Let Gaussians Deform with Scale-specific Mipmap for Anti-aliasing Rendering

https://github.com/renderme-360/renderme-360

공식 코드

RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars

https://github.com/ruijiezhu94/ti-face

공식 코드

TIFace: Improving Facial Reconstruction through Tensorial Radiance Fields and Implicit Surfaces

https://github.com/russrobin/knowledge_nerf

공식 코드

Knowledge NeRF: Few-shot Novel View Synthesis for Dynamic Articulated Objects

https://github.com/ruyi-zha/naf_cbct

공식 코드

NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction

https://github.com/rzhevcherkasy/bmvc24-gsim

공식 코드

Gaussian Splatting in Mirrors: Reflection-Aware Rendering via Virtual Camera Optimization

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.