Three-dimensional (3D) microscopy data is often anisotropic with significantly lower resolution (up to \(8{\times }\) ) along the z axis than along the xy axes. Computationally generating plausible isotropic resolution from anisotropic imaging data would benefit the visual analysis of large-scale volumes. This paper proposes niiv, a self-supervised method for isotropic reconstruction of 3D microscopy data that can quickly produce images at arbitrary output resolutions. The representation embeds a learned latent code within a neural field that describes the implicit higher-resolution isotropic image region. We use an attention-guided latent interpolation approach, which allows flexible information exchange over a local latent neighborhood. Under isotropic volume assumptions, we self-supervise this representation on low-/high-resolution lateral image pairs to reconstruct an isotropic volume from low-resolution axial images. We evaluate our method on simulated and real anisotropic electron (EM) and light microscopy (LM) data. Compared to diffusion-based baselines, niiv shows improved reconstruction quality (+1 dB PSNR) and is over three orders of magnitude faster (1,000 \(\times \) ) to infer. Specifically, niiv reconstructs a \(128^3\) voxel volume in th of a second, renderable at varying (continuous) high resolutions for display. Our code is available at https://github.com/jakobtroidl/niiv-miccai .