paper-with-me

Papers

Multi-View Transformer for 3D Visual Grounding

2022-04-05 · CVPR 2022 1 · Shijia Huang, Yilun Chen, Jiaya Jia, LiWei Wang

The 3D visual grounding task aims to ground a natural language description to the targeted object in a 3D scene, which is usually represented in 3D point clouds. Previous works studied visual grounding under specific views. The vision-language correspondence learned by this way can easily fail once the view changes. In this paper, we propose a Multi-View Transformer (MVT) for 3D visual grounding. We project the 3D scene to a multi-view space, in which the position information of the 3D scene under different views are modeled simultaneously and aggregated together. The multi-view space enables the network to learn a more robust multi-modal representation for 3D visual grounding and eliminates the dependence on specific views. Extensive experiments show that our approach significantly outperforms all state-of-the-art methods. Specifically, on Nr3D and Sr3D datasets, our method outperforms the best competitor by 11.2% and 7.1% and even surpasses recent work with extra 2D assistance by 5.9% and 6.6%. Our code is available at https://github.com/sega-hsj/MVT-3DVG.

📄 PDF Abstract BibTeX arXiv:2204.02174

Code (1)

sega-hsj/mvt-3dvg 공식 구현 pytorch

Tasks

3D visual groundingVisual Grounding

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding

2023-01-01 · ICCV 2023 1 · Zoey Guo, Yiwen Tang, Ray Zhang, Dong Wang 외

Understanding 3D scenes from multi-view inputs has been proven to alleviate the view discrepancy issue in 3D visual grounding. However, existing methods normally neglect the view cues embedded in the text modality an…

3D visual groundingVisual Grounding

ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance

2023-03-29 · Zoey Guo, Yiwen Tang, Ray Zhang, Dong Wang 외

Understanding 3D scenes from multi-view inputs has been proven to alleviate the view discrepancy issue in 3D visual grounding. However, existing methods normally neglect the view cues embedded in the text modality and fa…

3D visual groundingVisual Grounding

MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding

2024-03-05 · CVPR 2024 1 · Chun-Peng Chang, Shaoxiang Wang, Alain Pagani, Didier Stricker

3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting c…

3D visual groundingDecision MakingObjectObject Recognition+1

ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition

2025-07-15 · Ronggang Huang, Haoxin Yang, Yan Cai, Xuemiao Xu 외

3D visual grounding aims to identify and localize objects in a 3D space based on textual descriptions. However, existing methods struggle with disentangling targets from anchors in complex multi-anchor queries and resolv…

3D visual groundingVisual Grounding

TransVG: End-to-End Visual Grounding with Transformers

2021-04-17 · ICCV 2021 10 · Jiajun Deng, Zhengyuan Yang, Tianlang Chen, Wengang Zhou 외

In this paper, we present a neat yet effective transformer-based framework for visual grounding, namely TransVG, to address the task of grounding a language query to the corresponding region onto an image. The state-of-t…

Referring Expression ComprehensionVisual Grounding