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

Showing 2650 of 271 papers

TitleStatusHype
NeRD: Neural Reflectance Decomposition from Image CollectionsCode1
Advances in Neural RenderingCode1
Outdoor inverse rendering from a single image using multiview self-supervisionCode1
PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance RegularizationCode1
PhyIR: Physics-Based Inverse Rendering for Panoramic Indoor ImagesCode1
Invertible Neural BRDF for Object Inverse RenderingCode1
MAIR++: Improving Multi-view Attention Inverse Rendering with Implicit Lighting RepresentationCode1
Multi-view Inverse Rendering for Large-scale Real-world Indoor ScenesCode1
IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray TracingCode1
High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse RenderingCode1
A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse RenderingCode1
IBL-NeRF: Image-Based Lighting Formulation of Neural Radiance FieldsCode1
IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View SynthesisCode1
Building 3D Morphable Models from a Single ScanCode1
InverseRenderNet: Learning single image inverse renderingCode1
Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion ModelCode1
Learning a 3D Morphable Face Reflectance Model from Low-cost DataCode1
Uncertainty for SVBRDF Acquisition using Frequency AnalysisCode1
MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting EstimationCode1
Diffusion Posterior Illumination for Ambiguity-aware Inverse RenderingCode1
Mesh Density Adaptation for Template-based Shape ReconstructionCode1
Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting EstimationCode1
GIR: 3D Gaussian Inverse Rendering for Relightable Scene FactorizationCode1
Multiview Textured Mesh Recovery by Differentiable RenderingCode1
Efficient Meshy Neural Fields for Animatable Human AvatarsCode1
Show:102550
← PrevPage 2 of 11Next →

Benchmark Results

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