GraLoD, a plug-and-play framework that treats restoration scale as a spatially varying and stage-dependent continuous variable, is proposed and minimal-sufficient footprint calibration (MSFC) together with structure-aware regularization (SAR) is introduced to encourage restoration-effective and spatially coherent LOD a...
This work proposes RestoreMore, a continual capability-expansion framework that preserves the pretrained restoration model as a frozen capability anchor and learns residual expansion modules for newly arriving degradations.
This work proposes to adopt fatigue as a proxy of the finite energy limit, inject it into general character animation, and thoroughly investigate how fatigue introduces new characteristics to physics-based character control.
Shengyuan Zhang, Xinpeng Liu, Mu-Chun Niu et al.· 0 citations
Recognizing that diverse multi-reference tasks share a common set of atomic operations, this work formalizes four operators: Anchor, Disentangle, Disentangle, Apply, and Compose, and constructs TRACE-Bench, comprising approximately 1,600 evaluation cases across slot counts 1--8.
Haoran Wang, Chaofan Ma, Ran Yi et al.· 0 citations
This work proposes Visual In-context Editing, a new paradigm elevating video editing from textual instructions to multi-modal visual guidance encompassing single image, image pair, and video pair, and curates VicEdit-400K, the first large-scale dataset for visual in-context video editing.
Yu-Ji Wang, Teng Hu, Yu-Heng Chen et al.· 0 citations
This work proposes GroupForward, an instance-grouped feed-forward Gaussian splatting model that reconstructs geometry, appearance, instance structure, and semantics from sparse, unposed, and uncalibrated multi-view images and proposes a Referential Scene Reasoning Framework (RSRF) for complex 3D referring segmentation.
Qi-Jian Tian, Zimeng Wu, Xu-Hong Wang et al.· 0 citations
This work proposes Change and Invariance Motion Editing (CIME), a unified framework that comprehensively decouples change and invariance into spatial pose and temporal rhythm dimensions and introduces the Riemannian Non-uniform Integral Manifold Mapping module.
Shao-Hui Lin, Zhenwu Shi, Jing-Yu Gong et al.· 1 citation· ⚡1
This work proposes Cycle-World, a novel framework designed for stable and temporally consistent long-video generation that tackles error drift by enforcing strict temporal reversibility across both the training and inference phases, and demonstrates that forward generative drift can be strictly bottlenecked by a cycle-...
Zihan Su, Teng Hu, Jiangning Zhang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
