SOTAVerified

Inverse Rendering

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–175 of 271 papers

TitleStatusHype
Robust Category-Level 3D Pose Estimation from Synthetic Data—0
Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior—0
Scattering Parameters and Surface Normals from Homogeneous Translucent Materials using Photometric Stereo—0
ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering—0
SfSNet: Learning Shape, Reflectance and Illuminance of Faces `in the Wild'—0
Shading Annotations in the Wild—0
Shading Meets Motion: Self-supervised Indoor 3D Reconstruction Via Simultaneous Shape-from-Shading and Structure-from-Motion—0
SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild—0
Simultaneous Estimation of Near IR BRDF and Fine-Scale Surface Geometry—0
Single-Image 3D Human Digitization with Shape-Guided Diffusion—0
Single-Shot Neural Relighting and SVBRDF Estimation—0
SIR: Multi-view Inverse Rendering with Decomposable Shadow for Indoor Scenes—0
Spatially and color consistent environment lighting estimation using deep neural networks for mixed reality—0
Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences using Transformer Networks—0
Spectral MVIR: Joint Reconstruction of 3D Shape and Spectral Reflectance—0
SS-SfP:Neural Inverse Rendering for Self Supervised Shape from (Mixed) Polarization—0
SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generation—0
SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering—0
Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video—0
Survey of Deep Learning Methods for Inverse Problems—0
TileGen: Tileable, Controllable Material Generation and Capture—0
TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians—0
TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light—0
Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces—0
Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion—0
Show:102550
← PrevPage 7 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Neural-PBIRHDR-PSNR26.01—Unverified
2NVDiffRecMCHDR-PSNR24.43—Unverified
3InvRenderHDR-PSNR23.76—Unverified
4NeRFactorHDR-PSNR23.54—Unverified
5NeRDHDR-PSNR23.29—Unverified
6NVDiffRecHDR-PSNR22.91—Unverified
7PhySGHDR-PSNR21.81—Unverified