AR News
Augmented reality gaming and development
arXiv cs.GR details CADSplat, a sparse-view 3D Gaussian splatting pipeline that uses CAD models to reconstruct photorealistic digital twins from fewer than 15 posed images. For teams building AR, inspection, …
GamesIndustry.biz reports that Polyarc Games is shutting down after 12 years, ending the studio behind Moss and Glassbreakers. The Seattle team said it is winding down active development, and it …
AR guidance for needle insertion gets a practical reality check: a phantom study found that the best visual cue depends on both user expertise and the surrounding display context. Novices …
Mixed and augmented reality are getting a more rigorous map for medical visualization. A new taxonomy breaks the field into image modality, data dimensionality, display tech, and clinical use, while …
NeRF-based reconstruction came out ahead in a study of holographic lab-object capture, especially for transparent, reflective, and low-texture items. The comparison against photogrammetry, Gaussian splatting, and LiDAR suggests shape and …
MetaSapiens v2 pushes real-time neural rendering toward practical VR/AR use, claiming an order-of-magnitude speedup while preserving visual quality. The system combines foveation-aware pruning, peripheral-quality reduction, stereo warping, and a binocular …
Researchers have built Capybara, an AR and AI visual programming environment that lets children create and animate 3D characters in the real world. It combines text-to-3D generation, auto-rigging, body tracking, …
A new study on hybrid immersive art finds that projection-to-HMD transitions break presence when alignment, appearance, or latency drift apart. In a 24-person within-subjects test, the inconsistent setup raised workload …
A new single-image avatar pipeline can generate photorealistic 3D head models with real-time expression control. S-Avatar combines diffusion-guided 3D Gaussian splatting with FLAME alignment to improve view consistency under motion …
AR glasses are running into a familiar wall: display quality versus battery life. LowPowAR tackles that by treating tone mapping as a power-budget problem and using a learning-based pipeline to …
Khronos says OpenXR is adding tiered Adopter fees to make official conformance easier for smaller XR vendors. The change keeps the same test bar, but lowers the cost of getting …
A new parallax-corrected video see-through display pipeline aims to make transparent overlays behave more like a stable HUD than a warped camera feed. The setup uses two cameras and a …
A new motion-capture approach uses just two or more people wearing smart glasses to reconstruct human movement in 3D. EgoExoMoCap blends egocentric and exocentric signals, plus head and optional wrist …
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 …
Niantic Spatial is shutting down its New Zealand office as the company continues pivoting away from games and entertainment. For developers, it’s another sign that AR and location-based teams are …
A 2026 TOG paper describes a transformer-based hand mocap system aimed at messy, interactive hand poses rather than clean lab captures. For teams building VR, AR, or first-person interaction, the …
A diffusion-based makeup transfer paper claims a big step toward production-ready AR/VTO: +60% facial recognition similarity and -50% skin-tone drift versus Stable-Makeup. The practical win for game teams is better …
Wave-optics holography is getting closer to something game teams could actually prototype with. This paper combines path tracing with the Rayleigh–Sommerfeld integral, so it can preserve depth continuity, view-dependent effects, …
Niantic says scans from millions of Pokémon Go players helped train a geospatial AI model now aimed at delivery robots and possibly military drones. For devs, the interesting part is …
HairPort tackles hairstyle transfer when source and target faces differ in pose, scale, or viewpoint. The pipeline first removes hair with a LoRA-adapted bald generator, then reconstructs and re-renders the …