Anton Obukhov

11

Papers

40

Total Citations

Papers (11)

Video Depth without Video Models

Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion

Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds

Learning To Relate Depth and Semantics for Unsupervised Domain Adaptation

Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields Translation

Exploring Relational Context for Multi-Task Dense Prediction

EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation

DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models

Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference

Towards Practical Control of Singular Values of Convolutional Layers