REVIEW 7 cited by
Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising
read the original abstract
Recent advances in differentiable rendering have enabled high-quality reconstruction of 3D scenes from multi-view images. Most methods rely on simple rendering algorithms: pre-filtered direct lighting or learned representations of irradiance. We show that a more realistic shading model, incorporating ray tracing and Monte Carlo integration, substantially improves decomposition into shape, materials & lighting. Unfortunately, Monte Carlo integration provides estimates with significant noise, even at large sample counts, which makes gradient-based inverse rendering very challenging. To address this, we incorporate multiple importance sampling and denoising in a novel inverse rendering pipeline. This substantially improves convergence and enables gradient-based optimization at low sample counts. We present an efficient method to jointly reconstruct geometry (explicit triangle meshes), materials, and lighting, which substantially improves material and light separation compared to previous work. We argue that denoising can become an integral part of high quality inverse rendering pipelines.
Forward citations
Cited by 7 Pith papers
-
AEGIR: Modeling Area Emitters for Indoor Inverse Rendering using Gaussian Splatting
AEGIR explicitly models local area emitters inside a relightable Gaussian Splatting pipeline and uses a differentiable deferred renderer with multiple importance sampling plus regularization to jointly optimize emitte...
-
Learning a Delighting Prior for Facial Appearance Capture in the Wild
A delighting network trained via Dataset Latent Modulation on heterogeneous OLAT and Light Stage data enables high-quality in-the-wild facial reflectance capture from video and produces the NeRSemble-Scan dataset.
-
Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere
Spherical Voronoi—a softmax partition of the sphere with learnable sites—is proposed as a differentiable appearance basis for Gaussian splatting, improving view-dependent radiance and reflection modeling.
-
AEGIR: Modeling Area Emitters for Indoor Inverse Rendering using Gaussian Splatting
AEGIR introduces explicit area-emitter modeling inside a relightable Gaussian Splatting pipeline together with a differentiable deferred renderer using multiple importance sampling and regularization to improve lighti...
-
TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructions
Hybrid system that uses ray-traced 3D Gaussians to supply radiometric guidance and material regularization to a neural renderer for editable, realistic output from captured scenes.
-
GaNI: Global and Near Field Illumination Aware Neural Inverse Rendering
GaNI combines NeuS geometry reconstruction with a light-position-aware inverse neural radiosity stage that adds implicit near-field modeling, surface angle loss, and roughness smoothness priors to recover reflectance ...
-
Efficiently Linking Real Scenes with Synthetic Data Generation for AI-based Cognitive Robotics and Computer Vision Applications
The paper reviews limits in AI vision for robotics and describes work-in-progress on bridging sim-to-real domain gaps by linking real and synthetic training data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.