Yixin Chen
Qing Li
Qing Li
SG3D
Description: PQ3D
A unified model for 3D vision-language (3D-VL) understanding is expected to take various scene representations and perform a wide range of tasks in a 3D scene. However, a considerable gap exists between existing methods and such a unified model, due to the independent application of representation and insufficient exploration of 3D multi-task training. In this paper, we introduce PQ3D, a unified model capable of using Promptable Queries to tackle a wide range of 3D-VL tasks, from low-level instance segmenta
This is achieved through three key innovations: (1) unifying various 3D scene representations (i.e., voxels, point clouds, multi-view im- ages) into a shared 3D coordinate space by segment-level grouping, (2) an attention-based query decoder for task-specific information retrieval guided by prompts, and (3) universal output heads for different tasks to support multi-task training.
PQ3D demonstrates impressive performance on these tasks, setting new records on most benchmarks. Particularly, PQ3D improves the state- of-the-art on ScanNet200 by 1.8% (AP), ScanRefer by 5.4% ([email protected]), Multi3DRefer by 11.7% ([email protected]), and Scan2Cap by 13.4% ([email protected]).Moreover, PQ3D supports flexible inference with individual or combined forms of available 3D representations, e.g., solely voxel input
Yixin Chen
Qing Li
Qing Li
SG3D