activity
20232026
collaborators

5 papers

cs.CV2026

PixSDS: Why Latent SDS Makes Noisy Pixels

Vsevolod Skorokhodov

Score Distillation Sampling (SDS) enables text-to-3D generation by optimizing rendered images with a pretrained diffusion prior, but latent SDS often produces structured color arti…

cs.CV2026

Spline-Based Boundary Representations for Sparse View Reconstruction and Simulation Using Isogeometric Analysis

Davor Dobrota, Vsevolod Skorokhodov, Chenghao Xu +2

Image-based reconstruction aims to recover three-dimensional geometry from images. Recent advances have enabled the recovery of visually detailed models, yet their representations…

cs.CV2026

SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for Unpaired RGB+Thermal 3D Reconstruction

Vsevolod Skorokhodov, Chenghao Xu, Shuo Sun +2

Foundational feed-forward visual geometry models enable accurate and efficient camera pose estimation and scene reconstruction by learning strong scene priors from massive RGB data…

cs.CV2025

Diffusion Models are Secretly Zero-Shot 3DGS Harmonizers

Vsevolod Skorokhodov, Nikita Durasov, Pascal Fua

Gaussian Splatting has become a popular technique for various 3D Computer Vision tasks, including novel view synthesis, scene reconstruction, and dynamic scene rendering. However,…

cs.CV2023

uSF: Learning Neural Semantic Field with Uncertainty

Vsevolod Skorokhodov, Darya Drozdova, Dmitry Yudin

Recently, there has been an increased interest in NeRF methods which reconstruct differentiable representation of three-dimensional scenes. One of the main limitations of such meth…