Search papers, labs, and topics across Lattice.
5
0
7
0
Existing methods for referring image segmentation struggle to focus on the target object, but TALENT solves this with a novel learning mechanism that dramatically improves segmentation accuracy.
By decoupling geometry and texture cues, GT-PCQA overcomes the texture bias of MLLMs to achieve state-of-the-art point cloud quality assessment, even with limited PCQA data.
Achieve efficient multi-robot coverage in complex, obstacle-filled environments by intelligently balancing workload across sub-regions using a Generalized Voronoi Graph.
Transferring image quality knowledge to point clouds can dramatically improve no-reference point cloud quality assessment, but only if you carefully align features by quality level and augment features in a quality-aware way.
The YT-NTU-AVQ dataset, 10x larger than previous AVQA datasets, unlocks new possibilities for training and evaluating multimodal perception models by offering unprecedented scale and diversity.
