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 61–70 of 271 papers

TitleStatusHype
DiffCSG: Differentiable CSG via Rasterization—0
MERLiN: Single-Shot Material Estimation and Relighting for Photometric Stereo—0
G3FA: Geometry-guided GAN for Face Animation—0
Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering—0
Progressive Radiance Distillation for Inverse Rendering with Gaussian Splatting—0
Many-Worlds Inverse Rendering—0
MAIR++: Improving Multi-view Attention Inverse Rendering with Implicit Lighting RepresentationCode1
PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance RegularizationCode1
PBIR-NIE: Glossy Object Capture under Non-Distant Lighting—0
Dynamic Scene Understanding through Object-Centric Voxelization and Neural RenderingCode1
Show:102550
← PrevPage 7 of 28Next →

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