Inverse Rendering News
The latest Inverse Rendering coverage curated for game developers.
Researchers have introduced an inverse rendering method that reconstructs fuzzy geometry with explicit line segments instead of volumetric primitives. The approach targets hair, fur, fibers, and textiles, aiming for real-time-friendly …
mmIR tackles a core radar bottleneck for simulation-heavy development: there still isn’t much high-resolution 3D millimeter-wave data to train or validate against. The system fits a physics-based forward model to …
A new intrinsic decomposition method tackles a long-standing misattribution problem in point-based 3D scene reconstruction. Intrinsic PAPR replaces translucent volume aggregation with proximity-aware point rendering so each surface point can …
RGBX-Next turns G-buffers into a controllable input for generative rendering, aiming to bridge the gap between diffusion models and traditional 3D pipelines. The system can synthesize realistic images, video, and …
A new CBCT reconstruction method uses Gaussian splatting plus polychromatic X-ray modeling to suppress metal artifacts and beam hardening. The system jointly optimizes reconstruction and spectral characteristics, avoiding manual metal …
A new cone-beam CT reconstruction method uses splat-based Gaussian representations plus a compact polychromatic attenuation model to cut metal artifacts without a metal mask. The approach targets the hard case …
DiffPhysCam brings differentiable, physics-based camera simulation to inverse rendering and embodied AI. It gives developers finer control over camera intrinsics, optical artifacts like defocus blur, and calibration against real data. …
IRGS++ pushes Gaussian splatting beyond pretty rasterized views by adding transport-aware inverse rendering for visibility and indirect light. The method targets inter-reflections, glossy and metallic materials, and novel relighting, aiming …
A new black-box inverse rendering pipeline, Feature-Informed Diffusion Evolution, skips gradients and hand-tuned initialization entirely. It uses ViT features to steer a diffusion model, then tightens candidates with CMA-ES. The …
A new inverse-rendering method tackles participating media by combining neural fields with physically complete light transport. The approach reconstructs spatially varying scattering, absorption, and phase functions from multi-view images, which …
A new inverse-rendering method uses rigid object motion to separate material from lighting more reliably. By tracking and reconstructing moving objects, the pipeline gets multiple light-surface interactions from a single …
Researchers have introduced a fully differentiable proxy for Unified Glare Rating, aiming to make glare a usable loss term in inverse rendering. The method adds a differentiable optical scattering pass …
AEGIR pushes relightable Gaussian Splatting closer to usable indoor lighting by modeling real area emitters instead of faking them as points or environment maps. That matters for anyone trying to …
For graphics teams working with 2D Gaussian splatting, the big change is that DR-GS stops baking lighting into the reconstruction. It separates geometry, illumination, and material so deformed objects can …
A 2026 TOG paper shows thermal non-line-of-sight imaging can work through rough surfaces, which is a meaningful step for sensing and reconstruction research. For game teams, the interesting part is …
A new inverse-rendering pipeline, NeuMatEx, tries to recover spatially varying neural materials from multi-view images instead of baking lighting into the result. The key trick is a Large Material Reconstruction …
For graphics programmers, the interesting bit is that this paper moves Gaussian splatting beyond per-primitive BRDF fitting. MaterialClusterGS uses a shared palette of material prototypes plus a continuous material field, …
A new inverse-rendering approach for 3D Gaussian fields tries to close a long-standing gap between training and final rendering. Instead of optimizing materials in screen space, it keeps forward rendering …
A new inverse-rendering pipeline uses active RGB-NIR capture to make geometry and reflectance estimation less sensitive to changing ambient light. The practical win is more stable reconstruction from real-world scenes, …
A single-shot inverse-rendering setup now uses an LCD to project polarized RGB binary patterns and an RGB polarization camera with a quarter-wave plate to recover normals, albedo, roughness, and metallicity. …