Text-driven human motion editing aims to realize a requested change while preserving compatible source content. Existing diffusion editors rely largely on learned conditioning for preservation of the unedited part, yet their outputs can lose temporal detail as denoising proceeds. We propose the \textbf{Source-Preservin...
Gold-Conditioned Distillation is proposed, a method that turns expert demonstrations into model-native supervision and improves new-task accuracy over SFT and generally reduces degradation on general benchmarks.
Wenxuan Zhu, Bang An, Shu-Ming Liu et al.· 0 citations
A new inference-time sampler for diffusion models that gives a pretrained model a capability it was never trained for: constructing the atlas of the population it synthesizes, which is the intrinsic atlas of the population it synthesizes.
Sparse-view novel view synthesis is a central problem in 3D content creation, but diffusion-based approaches remain limited by iterative denoising, making multi-view generation expensive at inference time. We introduce NAMVIS, a diffusion-free framework that reformulates multi-view image synthesis as geometry-condition...
R. Khafizov, I. Statsenko, Ruslan Rakhimov et al.· 0 citations
Modern stereo matching models fail when disparity crosses zero, with end-point error (EPE) rising by 4.6-37$\times$. Yet stereoscopic content, from cinema 3D to VR, routinely contains objects behind the zero-disparity plane (ZDP), corresponding to negative disparities. The blind spot cascades through datasets, architec...
Jian Shi, Xin-Ge Yang, Chao-Yang Wang et al.· 0 citations
AntPlan, a curated dataset of 505 real professional architectural floor plans with dense furniture annotations spanning 92 object classes and ten residential room categories, and Architect-Ant, a framework for generating furniture layouts are introduced, enabling direct constraint-aware layout generation without relyin...
F. Rodionov, Aleksandar Cvejic, Michael Birsak et al.· arXiv.org· 0 citations
An event-aware evaluation protocol that separately measures post-trigger editing quality, pre-trigger preservation, and false-trigger robustness is introduced.
Jinjie Mai, G. Qian, W. Menapace et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.