5 papers
Forget Superresolution, Sample Adaptively (when Path Tracing)
Martin Bálint, Corentin Salaün, Hans-Peter Seidel +1
Real-time path tracing increasingly operates under extremely low sampling budgets, often below one sample per pixel, as rendering complexity, resolution, and frame-rate requirement…
MILO: A Lightweight Perceptual Quality Metric for Image and Latent-Space Optimization
UÄur ÃoÄalan, Mojtaba Bemana, Karol Myszkowski +2
We present MILO (Metric for Image- and Latent-space Optimization), a lightweight, multiscale, perceptual metric for full-reference image quality assessment (FR-IQA). MILO is traine…
Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising
Mojtaba Bemana, Thomas Leimkühler, Karol Myszkowski +2
We demonstrate generating HDR images using the concerted action of multiple black-box, pre-trained LDR image diffusion models. Relying on a pre-trained LDR generative diffusion mod…
LEDiff: Latent Exposure Diffusion for HDR Generation
Chao Wang, Zhihao Xia, Thomas Leimkuehler +2
While consumer displays increasingly support more than 10 stops of dynamic range, most image assets such as internet photographs and generative AI content remain limited to 8-bit l…
Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field
Chao Wang, Krzysztof Wolski, Bernhard Kerbl +5
Radiance field methods represent the state of the art in reconstructing complex scenes from multi-view photos. However, these reconstructions often suffer from one or both of the f…