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/MARVELOUSJI/REFRAME
공식 코드REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices
https://github.com/MegaScenes/nvs
공식 코드https://github.com/MingyuY/deformable-view-synthesis
공식 코드Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder
https://github.com/Mirmix/muviecast
공식 코드https://github.com/NVlabs/CF-3DGS
공식 코드https://github.com/NVlabs/FoundationStereo
공식 코드FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
https://github.com/NVlabs/InstantSplat
공식 코드InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds
https://github.com/OpenDriveLab/MTGS
공식 코드https://github.com/POSTECH-CVLab/nvsadapter
공식 코드NVS-Adapter: Plug-and-Play Novel View Synthesis from a Single Image
https://github.com/PierreMarza/autonerf
공식 코드AutoNeRF: Training Implicit Scene Representations with Autonomous Agents
https://github.com/Pokerlishao/LoopGaussian
공식 코드LoopGaussian: Creating 3D Cinemagraph with Multi-view Images via Eulerian Motion Field
https://github.com/QuintonQu/gaussian-splatting-with-depth
공식 코드https://github.com/RenYurui/Global-Flow-Local-Attention
공식 코드Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation
https://github.com/RongLiu-Leo/AtomGS
공식 코드AtomGS: Atomizing Gaussian Splatting for High-Fidelity Radiance Field
https://github.com/RongLiu-Leo/beta-splatting
공식 코드https://github.com/RuijieZhu94/MotionGS
공식 코드MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
https://github.com/SanoScience/PR-ENDO
공식 코드PR-ENDO: Physically Based Relightable Gaussian Splatting for Endoscopy
https://github.com/ShijieZhou-UCLA/feature-3dgs
공식 코드Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
https://github.com/THU-luvision/OmniSeg3D
공식 코드OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning
https://github.com/TQTQliu/MVSGaussian
공식 코드MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo
https://github.com/TangZJ/3iGS
공식 코드3iGS: Factorised Tensorial Illumination for 3D Gaussian Splatting
https://github.com/Totoro97/NeuS
공식 코드NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
https://github.com/Totoro97/f2-nerf
공식 코드F$^{2}$-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories
https://github.com/USTC3DV/MERFStudio
공식 코드City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Web
https://github.com/VITA-Group/LightGaussian
공식 코드LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
https://github.com/VITA-Group/NeuralLift-360
공식 코드NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° Views
https://github.com/VITA-Group/SinNeRF
공식 코드SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image
https://github.com/Vinayak-VG/GAURA
공식 코드GAURA: Generalizable Approach for Unified Restoration and Rendering of Arbitrary Views
https://github.com/WU-CVGL/BAD-Gaussians
공식 코드https://github.com/WU-CVGL/BAD-NeRF
공식 코드https://github.com/WU-CVGL/USB-NeRF
공식 코드USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields
https://github.com/Wanggcong/SparseNeRF
공식 코드SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis
https://github.com/Wi-sc/ViewFusion
공식 코드ViewFusion: Towards Multi-View Consistency via Interpolated Denoising
https://github.com/XiangFeng66/SR-GS
공식 코드https://github.com/XiaoBin2001/EDC
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.