4 papers
Self-improving Multiplane-to-layer Images for Novel View Synthesis
Pavel Solovev, Taras Khakhulin, Denis Korzhenkov
We present a new method for lightweight novel-view synthesis that generalizes to an arbitrary forward-facing scene. Recent approaches are computationally expensive, require per-sce…
Image Generators with Conditionally-Independent Pixel Synthesis
Ivan Anokhin, Kirill Demochkin, Taras Khakhulin +3
Existing image generator networks rely heavily on spatial convolutions and, optionally, self-attention blocks in order to gradually synthesize images in a coarse-to-fine manner. He…
Simple heuristics for efficient parallel tensor contraction and quantum circuit simulation
Roman Schutski, Dmitry Kolmakov, Taras Khakhulin +1
Tensor networks are the main building blocks in a wide variety of computational sciences, ranging from many-body theory and quantum computing to probability and machine learning. H…
Graph Convolutional Policy for Solving Tree Decomposition via Reinforcement Learning Heuristics
Taras Khakhulin, Roman Schutski, Ivan Oseledets
We propose a Reinforcement Learning based approach to approximately solve the Tree Decomposition (TD) problem. TD is a combinatorial problem, which is central to the analysis of gr…