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.
3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos
Neural Mesh Fusion: Unsupervised 3D Planar Surface Understanding
RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation
GaussianPro: 3D Gaussian Splatting with Progressive Propagation
Flexible Physical Camouflage Generation Based on a Differential Approach
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting
Neural Rendering based Urban Scene Reconstruction for Autonomous Driving
OASim: an Open and Adaptive Simulator based on Neural Rendering for Autonomous Driving
AONeuS: A Neural Rendering Framework for Acoustic-Optical Sensor Fusion
DRSM: efficient neural 4d decomposition for dynamic reconstruction in stationary monocular cameras
On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy
GaussianStyle: Gaussian Head Avatar via StyleGAN
CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting
Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation
RPNR: Robust-Perception Neural Reshading
Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion
GPAvatar: Generalizable and Precise Head Avatar from Image(s)
Gaussian Shadow Casting for Neural Characters
Dubbing for Everyone: Data-Efficient Visual Dubbing using Neural Rendering Priors
Neural Rendering and Its Hardware Acceleration: A Review
What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs
Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior
Wild2Avatar: Rendering Humans Behind Occlusions
City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Web
SUNDIAL: 3D Satellite Understanding through Direct, Ambient, and Complex Lighting Decomposition
Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks
PNeRFLoc: Visual Localization with Point-based Neural Radiance Fields
TIFace: Improving Facial Reconstruction through Tensorial Radiance Fields and Implicit Surfaces
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments
ProNeRF: Learning Efficient Projection-Aware Ray Sampling for Fine-Grained Implicit Neural Radiance Fields
Global Latent Neural Rendering
COLMAP-Free 3D Gaussian Splatting
R2Human: Real-Time 3D Human Appearance Rendering from a Single Image
IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing
Towards Knowledge-driven Autonomous Driving
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.