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/yizhangphd/freqpcr

공식 코드

Frequency-Modulated Point Cloud Rendering with Easy Editing

https://github.com/ymhe12/GS-Phong

공식 코드

GS-Phong: Meta-Learned 3D Gaussians for Relightable Novel View Synthesis

https://github.com/ysus33/rgb-d_plenoxel_mapping_tracking

공식 코드

RGB-D Mapping and Tracking in a Plenoxel Radiance Field

https://github.com/yueyin27/refref

공식 코드

RefRef: A Synthetic Dataset and Benchmark for Reconstructing Refractive and Reflective Objects

https://github.com/yukexing/3dgs-ieval-15k

공식 코드

3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting

https://github.com/yvanliang/DriveEditor

공식 코드

DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes

https://github.com/yxlao/corres-nerf

공식 코드

CorresNeRF: Image Correspondence Priors for Neural Radiance Fields

https://github.com/zcsrenlongz/deblur4dgs

공식 코드

Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video

https://github.com/zehao-wang/indoortraj

공식 코드

Diversity-Driven View Subset Selection for Indoor Novel View Synthesis

https://github.com/zhang-fengdi/ControlGS

공식 코드

Consistent Quantity-Quality Control across Scenes for Deployment-Aware Gaussian Splatting

https://github.com/zhanglbthu/prtgaussian

공식 코드

PRTGaussian: Efficient Relighting Using 3D Gaussians with Precomputed Radiance Transfer

https://github.com/zhengxyun/PKU-DyMVHumans

공식 코드

PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling

https://github.com/zhenpeiyang/hm3d-abo

공식 코드

HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction

https://github.com/zhihao-lin/neurmips

공식 코드

NeurMiPs: Neural Mixture of Planar Experts for View Synthesis

https://github.com/zhihaohaoran/GPGS

공식 코드

GP-GS: Gaussian Processes for Enhanced Gaussian Splatting

https://github.com/zhu-zhiyu/nvs_solver

공식 코드

NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer

https://github.com/zhuhao-nju/mofanerf

공식 코드

MoFaNeRF: Morphable Facial Neural Radiance Field

https://github.com/ziplab/ZPressor

공식 코드

ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

https://github.com/zixunh/3DGEER

공식 코드

3DGEER: Exact and Efficient Volumetric Rendering with 3D Gaussians

https://github.com/zju3dv/EnvGS

공식 코드

EnvGS: Modeling View-Dependent Appearance with Environment Gaussian

https://github.com/zju3dv/im4d

공식 코드

Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes

https://github.com/zju3dv/intrinsicnerf

공식 코드

IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis

https://github.com/zju3dv/neuralbody

공식 코드

Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans

https://github.com/zparquet/fast-learning

공식 코드

Fast Learning Radiance Fields by Shooting Much Fewer Rays

https://github.com/zpbao/bowtie_networks

공식 코드

Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis

https://github.com/zqlin0521/cdgs-release

공식 코드

CDGS: Confidence-Aware Depth Regularization for 3D Gaussian Splatting

https://github.com/zsh2000/muvienerf

공식 코드

Multi-task View Synthesis with Neural Radiance Fields

https://github.com/zubair-irshad/NeO-360

공식 코드

NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes

https://github.com/zyp123494/dynavol

공식 코드

Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering

https://github.com/zyqz97/aerial_lifting

공식 코드

Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery

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