Human-art: A versatile human-centric dataset bridging natural and artificial scenes
Humans have long been recorded in a variety of forms since antiquity. For example,
sculptures and paintings were the primary media for depicting human beings before the …
sculptures and paintings were the primary media for depicting human beings before the …
Panic-3d: Stylized single-view 3d reconstruction from portraits of anime characters
We propose PAniC-3D, a system to reconstruct stylized 3D character heads directly from
illustrated (p) ortraits of (ani) me (c) haracters. Our anime-style domain poses unique …
illustrated (p) ortraits of (ani) me (c) haracters. Our anime-style domain poses unique …
VLPose: Bridging the Domain Gap in Pose Estimation with Language-Vision Tuning
J Li, P Chen, X Ju, H Xu, J Jia - arXiv preprint arXiv:2402.14456, 2024 - arxiv.org
Thanks to advances in deep learning techniques, Human Pose Estimation (HPE) has
achieved significant progress in natural scenarios. However, these models perform poorly in …
achieved significant progress in natural scenarios. However, these models perform poorly in …
Synthetic Football Sprite Animations Learned Across the Pitch
A Ionascu, S Stefaniga, M Gaianu - International Conference on …, 2023 - Springer
In previous sporting scene synthesis and 3D reconstruction pipelines, gathering an
extensive database of sprite animations has been problematic and often the cause of …
extensive database of sprite animations has been problematic and often the cause of …