Diffusion-based models enable monocular geometry estimation, yet their pixel-space precision is limited by a shared, under-studied error source: VAE reconstruction degradation. The 8x spatial compression in the VAE encoder-decoder degrades surface normals at object boundaries; even encoding and decoding ground-truth no...
SmartMage is proposed, a unified MLLM that dynamically orchestrates heterogeneous modalities for semantic-aware 3D scene understanding and achieves state-of-the-art performance across five 3D scene understanding benchmarks, and attains competitive results on RGB-only video understanding benchmarks.
Yue Zhang, Yingzhao Jian, Yunqi Xu et al.· 0 citations
SPACE introduces a Depth-Adaptive HVI Transformation to decouple luminance and chrominance under depth guidance, effectively suppressing color-space noise and a Depth-Manifold Modulated Attention mechanism constrains feature interactions within a learned depth manifold, ensuring structural coherence during enhancement.
Yue Zhang, Zhi-Liang Wu, Yuxuan Hou et al.· Proceedings of the Thirty-Fi...· 0 citations
LEMO Agent is presented, a large-language-model agent framework for closed-loop inverse design of gas-separation MOFs in MOFid space that enriches high-performing candidates, improves predicted separation performance, and maintains broad chemical and topological diversity.
Zhaolin Hu, Hehe Fan, Wangyihan Guo et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
