Global Illumination News
The latest Global Illumination coverage curated for game developers.
A new global illumination method packs light transport into a 13D Gaussian mixture over position, direction, normals, and material. The result is millisecond-scale, view-independent rendering with far less memory than …
AMD GPUOpen details a one-step latent diffusion approach for real-time global illumination that aims to keep lighting stable without iterative denoising passes. For graphics programmers, the pitch is better GI …
A new graphics paper proposes a maximum-entropy way to compress directional irradiance into finite spherical moments while guaranteeing non-negative reconstruction. The method uses total energy plus first- and second-order directional …
AMD GPUOpen details a lightweight attention-based neural GI model that reconstructs off-screen indirect illumination from reflective shadow maps. The pitch is practical for teams chasing better bounce lighting without a …
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 …
Unity is moving toward real-time global illumination, closing a major lighting gap with Unreal’s Lumen and Godot’s SDFGI. For teams chasing dynamic day-night cycles or destructible environments, that could mean …
A new real-time GI technique, Split Radiance Cascades, targets full 3D diffuse lighting with sparse world-space probes instead of screenspace tricks. It combines a hashmap-backed probe layout with ray splitting …
Unity says Unity 7 is coming with CoreCLR, faster play mode, and a rebuilt reload model aimed at cutting iteration time. The company also teased Surface Cache GI, DXC support, …
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 …
Disney Research Studios is pushing path guiding beyond simple sample-count splits by making the k-d tree react to illumination variation. The method adds lookahead cells that hold compact light-field signatures, …
RenderFormer++ tackles feed-forward neural global illumination with two practical upgrades: physics-informed transport guidance and hierarchical object-centric tokenization. The result is a model aimed at better cross-scene generalization while cutting the …
A new rendering primitive based on 3D Gaussian distributions aims to bridge the gap between mesh, voxel, and splat workflows. The paper argues it can handle glossy surfaces, fuzzy materials, …
A new 3D light-transport embedding aims to predict global illumination directly from scene geometry and materials, instead of leaning on screen-space cues or per-scene training. For graphics teams, the interesting …
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 52 MB neural field can turn a trained 3D Gaussian Splatting scene into a constant-time ray oracle, which is a big deal for secondary rays. The paper reports 26–72x …
Neural Dynamic GI introduces a groundbreaking compression technique for temporal lightmaps, significantly reducing storage needs while maintaining high-quality global illumination. This innovation is particularly relevant for graphics programmers and artists …