Volume Rendering News
The latest Volume Rendering coverage curated for game developers.
MedVA tackles a stubborn bottleneck in medical volume visualization: turning a clinician’s intent into the right ROI and making it visible without endless manual tuning. The system combines symbolic reasoning, …
A new Gaussian-volume encoding method packs scalar fields into a fixed primitive budget, then refines those primitives directly against the source data without densification or pruning. In tests, it cut …
A new clipping method for medical volume Gaussian splatting can render cutaway views exactly, instead of crudely keeping or dropping whole splats. XClipGS also stays differentiable and hits over 650 …
A new sparse volume rendering method, ESVR, pushes large-scale volumetric visualization toward real-time use with ellipsoid primitives instead of dense voxels. It learns directly from 3D data, supports interactive transfer-function …
A new rendering framework for time-varying implicit neural volumes reaches 30-40 FPS at 1024x1024 on an RTX 4090 while keeping timestep changes to about 1-2 ms. It replaces dense ray …
A new Gaussian volumetric representation aims to make shear-warp visualization fast enough for dense medical volumes, while preserving anatomical and radiometric detail. The method trains from sparse voxel supervision using …
A new paper reframes SDF-based surface rendering as a probabilistic first-passage problem, which is interesting if you work on reconstruction or any renderer that needs uncertainty estimates. The authors say …
A browser-native WebGPU renderer hits under 920 ms time-to-first-pixel and stays above 82 FPS on low-cost integrated GPUs. The interesting part for game devs is the client-side raymarching pipeline: deterministic …
NeuVolEx introduces a novel approach to volume exploration using implicit neural representations (INRs). This advancement is particularly relevant for graphics programmers and designers, as it enhances the classification and clustering …
Gabor Fields brings orientation-selective level-of-detail to volume rendering, aiming to cut memory and traversal cost without the usual mipmap headaches. The technique prunes Gaussian primitives by frequency and orientation, preserving …
A new deep learning model, ENTIRE, promises to enhance volume rendering time predictions, crucial for graphics programmers. By accurately forecasting rendering times based on various parameters, it allows for better …