Papers with Code 아카이브
Inverse Rendering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 7
Inverse Rendering is the task of recovering the properties of a scene, such as shape, material, and lighting, from an image or a video. The goal of inverse rendering is to determine the properties of a scene given an observation of it, and to generate new images or videos based on these properties.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fields
MonoNPHM: Dynamic Head Reconstruction from Monocular Videos
GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization
IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing
Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance
Differentiable Point-based Inverse Rendering
The Sky's the Limit: Re-lightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility
GS-IR: 3D Gaussian Splatting for Inverse Rendering
NeISF: Neural Incident Stokes Field for Geometry and Material Estimation
Virtual Home Staging: Inverse Rendering and Editing an Indoor Panorama under Natural Illumination
Intrinsic Image Decomposition via Ordinal Shading
NePF: Neural Photon Field for Single-Stage Inverse Rendering
Holistic Inverse Rendering of Complex Facade via Aerial 3D Scanning
Single-Image 3D Human Digitization with Shape-Guided Diffusion
RENI++ A Rotation-Equivariant, Scale-Invariant, Natural Illumination Prior
DeepShaRM: Multi-View Shape and Reflectance Map Recovery Under Unknown Lighting
Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark
SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes
Diffusion Posterior Illumination for Ambiguity-aware Inverse Rendering
Joint Sampling and Optimisation for Inverse Rendering
Self-Calibrating, Fully Differentiable NLOS Inverse Rendering
OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects
A Theory of Topological Derivatives for Inverse Rendering of Geometry
Efficient Multi-View Inverse Rendering Using a Hybrid Differentiable Rendering Method
Relightable and Animatable Neural Avatar from Sparse-View Video
Mesh Density Adaptation for Template-based Shape Reconstruction
Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation
UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video
Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects
Robust Category-Level 3D Pose Estimation from Synthetic Data
Eclipse: Disambiguating Illumination and Materials using Unintended Shadows
NOVUM: Neural Object Volumes for Robust Object Classification
Inverse Rendering of Translucent Objects using Physical and Neural Renderers
ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering
Inverse Global Illumination using a Neural Radiometric Prior
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.