Papers with Code 아카이브
Neural Rendering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
Given a representation of a 3D scene of some kind (point cloud, mesh, voxels, etc.), the task is to create an algorithm that can produce photorealistic renderings of this scene from an arbitrary viewpoint. Sometimes, the task is accompanied by image/scene appearance manipulation.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Bootstrap-GS: Self-Supervised Augmentation for High-Fidelity Gaussian Splatting
MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing
SAGS: Structure-Aware 3D Gaussian Splatting
FaceFolds: Meshed Radiance Manifolds for Efficient Volumetric Rendering of Dynamic Faces
PGAHum: Prior-Guided Geometry and Appearance Learning for High-Fidelity Animatable Human Reconstruction
NeRF-DetS: Enhanced Adaptive Spatial-wise Sampling and View-wise Fusion Strategies for NeRF-based Indoor Multi-view 3D Object Detection
HashPoint: Accelerated Point Searching and Sampling for Neural Rendering
ArtNeRF: A Stylized Neural Field for 3D-Aware Cartoonized Face Synthesis
High-fidelity Endoscopic Image Synthesis by Utilizing Depth-guided Neural Surfaces
Inverse Neural Rendering for Explainable Multi-Object Tracking
RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Rendering
Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior
3D Gaussian Splatting as Markov Chain Monte Carlo
HFNeRF: Learning Human Biomechanic Features with Neural Radiance Fields
Flying with Photons: Rendering Novel Views of Propagating Light
3D Facial Expressions through Analysis-by-Neural-Synthesis
Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes
SGCNeRF: Few-Shot Neural Rendering via Sparse Geometric Consistency Guidance
HO-Gaussian: Hybrid Optimization of 3D Gaussian Splatting for Urban Scenes
SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior
Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence
XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold
Towards 3D Vision with Low-Cost Single-Photon Cameras
Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction
Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos
Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap
BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting
RoGUENeRF: A Robust Geometry-Consistent Universal Enhancer for NeRF
LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation
FLex: Joint Pose and Dynamic Radiance Fields Optimization for Stereo Endoscopic Videos
DPPE: Dense Pose Estimation in a Plenoxels Environment using Gradient Approximation
HourglassNeRF: Casting an Hourglass as a Bundle of Rays for Few-shot Neural Rendering
A survey of synthetic data augmentation methods in computer vision
Voxel-Mesh Hybrid Representation for Real-Time View Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.