https://github.com/j-alex-hanson/gaussian-splatting-pup
공식 코드PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting
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/jiang-wenxiang/ipa-nerf
공식 코드IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields
https://github.com/jianglongye/featurenerf
공식 코드FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models
https://github.com/jiangxb98/egsral
공식 코드https://github.com/jiaw-z/CoR-GS
공식 코드CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization
https://github.com/jiawei-yang/freenerf
공식 코드FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization
https://github.com/jiaxinxie97/hfgi3d
공식 코드High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization
https://github.com/jibo27/3dgs_hierarchical_training
공식 코드https://github.com/jimmyYliu/Animatable-3D-Gaussian
공식 코드Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars
https://github.com/jinnan-chen/HGM
공식 코드https://github.com/jkulhanek/tetra-nerf
공식 코드Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra
https://github.com/jkulhanek/viewformer
공식 코드ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers
https://github.com/jmhb0/view_neti
공식 코드https://github.com/johnminelli/twowaysynth
공식 코드Depth self-supervision for single image novel view synthesis
https://github.com/jokeryan/nerf-ds
공식 코드NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects
https://github.com/jwubz123/DIG3D
공식 코드LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians
https://github.com/jwubz123/UNIG
공식 코드UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images
https://github.com/kaikai23/maskgaussian
공식 코드MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks
https://github.com/ken-ouyang/PGMPI
공식 코드Real-Time Neural Character Rendering with Pose-Guided Multiplane Images
https://github.com/klmav-cuc/gdb-nerf
공식 코드Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction
https://github.com/klmav-cuc/golf-nrt
공식 코드GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis
https://github.com/ktiwary2/orca
공식 코드https://github.com/kxhit/EscherNet
공식 코드https://github.com/kyleolsz/TB-Networks
공식 코드https://github.com/kylesargent/zeronvs
공식 코드ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image
https://github.com/lastbasket/endo-2dtam
공식 코드https://github.com/leaplabthu/activenerf
공식 코드ActiveNeRF: Learning where to See with Uncertainty Estimation
https://github.com/learner-shx/svg-ir
공식 코드SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering
https://github.com/leon2000-ai/tsgaussian
공식 코드TSGaussian: Semantic and Depth-Guided Target-Specific Gaussian Splatting from Sparse Views
https://github.com/lfranke/trips
공식 코드TRIPS: Trilinear Point Splatting for Real-Time Radiance Field Rendering
https://github.com/lfranke/vet
공식 코드VET: Visual Error Tomography for Point Cloud Completion and High-Quality Neural Rendering
https://github.com/limacv/Deblur-NeRF
공식 코드https://github.com/linhanwang/DC-Gaussian
공식 코드DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos
https://github.com/liortalker/MindTheEdge
공식 코드Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation
https://github.com/liuff19/Semantic-Ray
공식 코드Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention
https://github.com/liuyuan-pal/NeuRay
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.