activity
20182026
most citedMarginDistillation: distillation for margin-based softmax

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

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV2026

NBAvatar: Neural Billboards Avatars with Realistic Hand-Face Interaction

David Svitov, Mahtab Dahaghin

We present NBAvatar - a method for realistic rendering of head avatars handling non-rigid deformations caused by hand-face interaction. We introduce a novel representation for anim…

cs.CV2025

CloseUpAvatar: High-Fidelity Animatable Full-Body Avatars with Mixture of Multi-Scale Textures

David Svitov, Pietro Morerio, Lourdes Agapito +1

We present a CloseUpAvatar - a novel approach for articulated human avatar representation dealing with more general camera motions, while preserving rendering quality for close-up…

cs.CV2024

BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis

David Svitov, Pietro Morerio, Lourdes Agapito +1

We present billboard Splatting (BBSplat) - a novel approach for novel view synthesis based on textured geometric primitives. BBSplat represents the scene as a set of optimizable te…

cs.CV2024

HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior

David Svitov, Pietro Morerio, Lourdes Agapito +1

We present HAHA - a novel approach for animatable human avatar generation from monocular input videos. The proposed method relies on learning the trade-off between the use of Gauss…

cs.CV2023

MoRF: Mobile Realistic Fullbody Avatars from a Monocular Video

Renat Bashirov, Alexey Larionov, Evgeniya Ustinova +4

We present a system to create Mobile Realistic Fullbody (MoRF) avatars. MoRF avatars are rendered in real-time on mobile devices, learned from monocular videos, and have high reali…

cs.CV2023

DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars

David Svitov, Dmitrii Gudkov, Renat Bashirov +1

We present DINAR, an approach for creating realistic rigged fullbody avatars from single RGB images. Similarly to previous works, our method uses neural textures combined with the…