arXiv:2603.24278v1 Announce Type: new
Abstract: The dominant paradigm for high-fidelity 3D generation relies on a VAE-Diffusion pipeline, where the VAE’s reconstruction capability sets a firm upper bound on generation quality. A fundamental challenge …
arXiv:2512.17143v2 Announce Type: replace
Abstract: Photographs of people taken by professional photographers typically present the person in beautiful lighting, with an interesting pose, and flattering quality. This is unlike common photos people tak…
arXiv:2603.24270v1 Announce Type: new
Abstract: While diffusion models excel at generating images with conventional dimensions, pushing them to synthesize ultra-high-resolution imagery at extreme aspect ratios (EAR) often triggers catastrophic structu…
arXiv:2512.16371v2 Announce Type: replace
Abstract: State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they still frequently fail to compose complex scenes or follow logical temporal instructions. In th…
arXiv:2512.10548v2 Announce Type: replace
Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress on various vision-language tasks, yet their visual perception remains limited. Humans, in comparison, perceive complex scene…
arXiv:2603.24257v1 Announce Type: new
Abstract: Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over ti…
arXiv:2512.06438v3 Announce Type: replace
Abstract: The generation of high-fidelity, animatable 3D human avatars remains a core challenge in computer graphics and vision, with applications in VR, telepresence, and entertainment. Existing approaches ba…
arXiv:2603.24245v1 Announce Type: new
Abstract: Micro-actions, fleeting and low-amplitude motions, such as glances, nods, or minor posture shifts, carry rich social meaning but remain difficult for current action recognition models to recognize due to…
arXiv:2603.24240v1 Announce Type: new
Abstract: Existing real-world super-resolution (RSR) methods based on generative priors have achieved remarkable progress in producing high-quality and globally consistent reconstructions. However, they often stru…
arXiv:2511.22533v2 Announce Type: replace
Abstract: Diffusion models have achieved impressive generative quality across modalities like 2D images, videos, and 3D shapes, but their inference remains computationally expensive due to the iterative denois…