activity
20172026
most citedDo Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark

10 citations · 12 across the 5 of their papers we have counts for

collaborators

9 papers

cs.CV2026

CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models

Vladislav Pyatov, Gleb Bobrovskikh, Saveliy Galochkin +6

We introduce CADFS, a data-centric framework that enables large vision-language models to generate complex CAD design histories. Existing generative CAD systems are restricted to s…

cs.CV2025★ 1 cited

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation

Daniil Selikhanovych, David Li, Aleksei Leonov +6

Diffusion models for super-resolution (SR) produce high-quality visual results but require expensive computational costs. Despite the development of several methods to accelerate d…

cs.CV2024

A3D: Does Diffusion Dream about 3D Alignment?

Savva Ignatyev, Nina Konovalova, Daniil Selikhanovych +9

We tackle the problem of text-driven 3D generation from a geometry alignment perspective. Given a set of text prompts, we aim to generate a collection of objects with semantically…

eess.IV2022

An Optimal Transport Perspective on Unpaired Image Super-Resolution

Milena Gazdieva, Petr Mokrov, Litu Rout +4

Real-world image super-resolution (SR) tasks often do not have paired datasets, which limits the application of supervised techniques. As a result, the tasks are usually approached…

cs.LG2021

Manifold Topology Divergence: a Framework for Comparing Data Manifolds

Serguei Barannikov, Ilya Trofimov, Grigorii Sotnikov +4

We develop a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models. We describe a novel tool, Cross-Barcode(P,Q), that, giv…

cs.LG2021★ 10 cited

Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark

Alexander Korotin, Lingxiao Li, Aude Genevay +3

Despite the recent popularity of neural network-based solvers for optimal transport (OT), there is no standard quantitative way to evaluate their performance. In this paper, we add…