Hyperspectral images (HSI) preserve material evidence lost in RGB, yet 3D material identification from multi-view HSI faces two obstacles. Spectral Gaussian splatting reconstructs spectra accurately but leaves unmixing to per-pixel post-processing, while multi-view hyperspectral capture is costly and real datasets lack pixel-level material labels and sub-pixel proportions. We propose Spectral World Renderer (SWR), a material-aware explicit representation that unifies 3D spectral reconstruction and unmixing: it fits a Gaussian scaffold from RGB and decodes ray-Gaussian intersections into abundances over a shared endmember dictionary. Additionally, appearance guidance prevents spectrally similar materials from merging when intensity absorbs their brightness differences. Moreover, SWR requires no material-label supervision during training. To address the data gap, we further construct the SWR Benchmark (SWR-Bench): a coding-agent pipeline generates eight indoor and outdoor worlds from measured reflectance, aligning HSI with both annotations. SWR achieves the highest mIoU in all eight worlds and the highest mean PSNR on each real dataset. On an 11-class urban world, it trains at least 3.67x faster than unmixing baselines; rendering averages 34.9 joint spectral and label views/s over four worlds on a single RTX 4090.
Single-image refocusing changes the focal plane and depth of field of a photograph after capture. Users compare focal choices on one photograph, so content stability across edits matters alongside quality and speed. Recent generative methods rerun large diffusion models for every edit, even when they first restore an all-in-focus image, so content can change inconsistently between edits. Yet only this restoration is highly ill-posed and benefits from a generative prior, whereas rendering blur is largely determined by depth and the focal plane. We therefore propose FlashReFocus, which runs diffusion once per photograph and renders each edit with a lightweight network. A one-step diffusion deblurrer with a decoder refiner recovers fine detail efficiently while balancing fidelity and perceptual quality. The renderer uses an explicit defocus map for control and defocus-bias attention to promote information exchange between tokens with similar blur magnitudes. Because every edit reuses the same reconstruction, in-focus content stays consistent across edits, and editing the map enables tilt-shift and two-plane effects. We further collect 3CReal, a benchmark of 89 pairs from three camera-lens systems, to evaluate generalization to unseen optics. For zero-shot bokeh rendering on EBB! Val176 and 3CReal, FlashReFocus leads the evaluated methods in fidelity and perceptual quality. At 1536x1536, a complete refocus takes 2.45 s and each subsequent edit 0.46 s on one RTX PRO 6000.