Diffusion-based models enable monocular geometry estimation, yet their pixel-space precision is limited by a shared, under-studied error source: VAE reconstruction degradation. The 8x spatial compression in the VAE encoder-decoder degrades surface normals at object boundaries; even encoding and decoding ground-truth no...
Interactive visual interfaces have become an important means of controlling generative image models, enabling users to manipulate generation through prompts, direct manipulation, and a range of interactions. However, existing techniques are typically presented as independent systems, making it difficult to understand h...
Susie S. Y. Li, Mingwei Li, Remco Chang· 0 citations
ZipLine introduces a predicate language that enables analysts to express patterns involving topology, node attributes, and neighborhood relations with a unified formalism, and provides a predicate-learning algorithm that maps analyst interactions across both topology and attribute views into the predicate language, ena...
Sjoerd Vink, Su-Yang Li, Brian Montambault et al.· arXiv.org· 0 citations
LatentGandr is a visual analytics technique that facilitates latent space exploration by extracting locally linear dimensions from embeddings in high-dimensional latent spaces by analyzing the topology and local curvature of the embeddings, and automatically identifies local neighborhoods and computes their principal c...
