naveen manwani (@NaveenManwani17)
2024-08-18 | ❤️ 50 | 🔁 11
🚨ECCV 2024 Paper Alert 🚨
➡️Paper Title: Unifying 3D Vision-Language Understanding via Promptable Queries
🌟Few pointers from the paper
🎯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, Authors have introduced “PQ3D”, a unified model capable of using Promptable Queries to tackle a wide range of 3D-VL tasks, from low-level instance segmentation to high-level reasoning and planning.
🎯This is achieved through three key innovations: ⚓Unifying various 3D scene representations (i.e., voxels, point clouds, multi-view images) into a shared 3D coordinate space by segment-level grouping. ⚓ An attention-based query decoder for task-specific information retrieval guided by prompts. ⚓ Universal output heads for different tasks to support multi-task training.
🎯Tested across ten diverse 3D-VL datasets, PQ3D demonstrates impressive performance on these tasks, setting new records on most benchmarks. Particularly, PQ3D improves the state-of-the-art on ScanNet200 by 4.9% (AP25), 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.
🏢Organization: @Tsinghua_Uni , Beijing Institute for General Artificial Intelligence (BIGAI)
🧙Paper Authors: Ziyu Zhu, Zhuofan Zhang, @jeasinema , Xuesong Niu, @_yixinchen , @BaoxiongJ , Zhidong Deng, @siyuanhuang95 , @Sealiqing
1️⃣Read the Full Paper here: https://arxiv.org/abs/2405.11442
2️⃣Project Page: https://pq3d.github.io/
3️⃣Code: https://github.com/PQ3D/PQ3D
4️⃣Demo:https://huggingface.co/spaces/li-qing/PQ3D-Demo
🎥 Be sure to watch the attached Technical Video -Sound on 🔊🔊
🎵 Music by Pavel Bekirov from @pixabay
Find this Valuable 💎 ?
♻️QT and teach your network something new
Follow me 👣, @NaveenManwani17 , for the latest updates on Tech and AI-related news, insightful research papers, and exciting announcements.
미디어
