by America Ortiz | Jul 1, 2026 | Machine Learning, Video Processing, Visual Computing
Neural Material Adapter: Transforming Complex Materials into Efficient Analytic BSDFs In this work, we present the Neural Material Adapter (NMA), a frameworkthat bridges the gap between high-fidelity material data and efficient rendering by mapping complex appearances...
by America Ortiz | May 31, 2026 | Video Processing, Visual Computing
What Is It Like to Be a Noise? An Entropy-based Gaussian Noise Regularization for Diffusion Models In this paper, we propose a Gaussianity regularizer that aligns a sample’s local statistics with a typical Gaussian realization, rather than relying on pointwise...
by America Ortiz | May 31, 2026 | Video Processing, Visual Computing
RenderFlow: Single-Step Neural Rendering via Flow Matching In this paper, we propose a novel, end-to-end, deterministic, single-step neural rendering framework, RenderFlow, built upon a flow matching paradigm. To further strengthen both rendering quality and...
by America Ortiz | May 31, 2026 | Video Processing, Visual Computing
Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation In this paper, we propose an algorithm for both memory and compute-efficient implementation of the all-pairs correlation volume sampling, still matching the exact mathematical operator as...
by America Ortiz | May 31, 2026 | Video Processing, Visual Computing
Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views In this paper, we propose a novel data curation pipeline that leverages image matting datasets for training and design a depth fixer network to automatically identify soft boundary...
