This work proposes a segmentation framework guided by Contrastive Language–Image Pre-training (CLIP) that enriches sparse 3D tokens with vision–language semantic priors and introduces a decoupled CLIP-induced semantic residual that forms semantic-geometric attention biases for local window attention.
Visual perception systems increasingly rely on hybrid sensing modalities, including RGB and event cameras, to operate robustly under complex and extreme environmental conditions. However, what fundamentally determines the respective advantages of RGB frames and dynamic events remains unclear. To this end, we introduc...
FuseAdapt is proposed, a parameter-efficient framework that performs fusion within the adaptation space of a frozen vision foundation model (VFM), exploring whether VFM priors can serve as an effective shared backbone for multi-modal segmentation.
BlenderWorld is introduced, the first comprehensive benchmark dedicated to evaluating frontier models on realistic 3D creation tasks, and reveals a critical bottleneck: while current models can parse broad instructions, they still profoundly struggle with fine-grained 3D spatial coherence and accurate structural reprod...
Accurate object-level 3D scene representation is the foundation of embodied intelligence and immersive multimedia interactions. However, existing semantic 3D Gaussian Splatting methods typically treat semantics as passive attributes of geometry. Such weakly coupled methods are highly prone to semantic aliasing at the b...
Recent advances in 3D reconstruction have progressed from per-scene optimization to feed-forward inference, and semantic scene understanding has followed suit -- yet existing methods remain confined to object-centric perception, neglecting spatial relations between objects. We formulate 3D spatial relation segmentation...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
