AI Paper Atlas

Research map / 3D vision / Face and shape

Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising

Jon Hasselgren, Nikolai Hofmann, Jacob Munkberg

NeurIPS 2022 · 3D vision › Face and shape · approach: Textured mesh generation · 38 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Monte Carlo direct illumination with ray tracing, multiple importance sampling, and denoising instead of the simpler lighting pipelinenvdiffrec-style inverse rendering · NeRFactor synthetic relightingPSNR: 24.8~dB -> 26.0~dBImproved
Use Monte Carlo direct illumination with ray tracing, multiple importance sampling, and denoising instead of the simpler lighting pipelinenvdiffrec-style inverse rendering · NeRF synthetic relightingPSNR: 23.3~dB -> 26.5~dBImproved
Use Monte Carlo direct illumination with ray tracing, multiple importance sampling, and denoising instead of the simpler lighting pipelinenvdiffrec-style inverse rendering · Our synthetic relightingPSNR: 23.7~dB -> 27.1~dBImproved
Use physically based material/light separation and regularization rather than the nvdiffrec pipelinenvdiffrec-style inverse rendering · NeRFactor synthetic view interpolationPSNR: 31.7~dB -> 29.6~dBHurt
Use physically based material/light separation and regularization rather than the nvdiffrec pipelinenvdiffrec-style inverse rendering · NeRF synthetic view interpolationPSNR: 30.4~dB -> 28.4~dBHurt
Use physically based material/light separation and regularization rather than the nvdiffrec pipelinenvdiffrec-style inverse rendering · Real-world view interpolationPSNR: 26.58~dB -> 25.29~dBHurt
Add denoising during optimization (ablation)Monte Carlo inverse rendering · Porsche reconstruction and environment lightingreconstruction qualityImproved
Use denoising at 8 spp rather than no denoising at 32 spp (ablation)Monte Carlo inverse rendering · Scene reconstructionreconstruction quality: 8~spp; 32~sppImproved
Fine-tune denoiser weights jointly with scene parameters rather than keeping denoiser weights fixed (ablation)Monte Carlo inverse rendering · Scene reconstructionreconstruction qualityHurt
Add the monochrome lighting regularizer (ablation)Monte Carlo inverse rendering · Hotdog, NeRF syntheticlighting/material separationImproved
Ramp in the shadow contribution during early optimization instead of applying the full shadow term immediately (ablation)Monte Carlo inverse rendering · Geometry reconstructiongeometry reconstructionImproved
Enable shadow visibility gradients (ablation)Joint shape, material, and lighting optimization · Three validation scenesPSNR: 29.06 -> 29.15; 26.83 -> 27.03; 28.21 -> 27.83Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy