# X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning

arXiv: https://arxiv.org/abs/2203.00843 · HTML: https://mlsanity.com/paper/2203.00843/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 48 of its 63 references that are in the map.
- First posted on arXiv 2 Mar 2022.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 48)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [Meshed-Memory Transformer for Image Captioning](https://mlsanity.com/paper/1912.08226/) (2019)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [Auto-Encoding Scene Graphs for Image Captioning](https://mlsanity.com/paper/1812.02378/) (2018)
- [Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning](https://mlsanity.com/paper/1612.01887/) (2016)
- [Scan2Cap: Context-aware Dense Captioning in RGB-D Scans](https://mlsanity.com/paper/2012.02206/) (2020)
- [Exploring Visual Relationship for Image Captioning](https://mlsanity.com/paper/1809.07041/) (2018)
- [DenseCap: Fully Convolutional Localization Networks for Dense Captioning](https://mlsanity.com/paper/1511.07571/) (2015)
- [Cross Modal Distillation for Supervision Transfer](https://mlsanity.com/paper/1507.00448/) (2015)
- [PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation](https://mlsanity.com/paper/1711.10871/) (2017)
- [Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings](https://mlsanity.com/paper/1803.08495/) (2018)
- [InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring](https://mlsanity.com/paper/2103.01128/) (2021)

## Built on by (most cited first, 30 of 70)

- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers](https://mlsanity.com/paper/2312.08168/) (2023)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding](https://mlsanity.com/paper/2401.09340/) (2024)
- [Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes](https://mlsanity.com/paper/2308.08769/) (2023)
- [Grounded 3D-LLM with Referent Tokens](https://mlsanity.com/paper/2405.10370/) (2024)
- [GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models](https://mlsanity.com/paper/2501.01428/) (2025)
- [EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding](https://mlsanity.com/paper/2209.14941/) (2022)
- [Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance](https://mlsanity.com/paper/2403.18036/) (2024)
- [End-to-End 3D Dense Captioning with Vote2Cap-DETR](https://mlsanity.com/paper/2301.02508/) (2023)
- [UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding](https://mlsanity.com/paper/2212.00836/) (2022)
- [3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer](https://mlsanity.com/paper/2501.01163/) (2025)
- [Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2311.15383/) (2023)
- [Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness](https://mlsanity.com/paper/2504.01901/) (2025)
- [ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities](https://mlsanity.com/paper/2407.01525/) (2024)
- [VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud](https://mlsanity.com/paper/2303.14408/) (2023)
- [TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes](https://mlsanity.com/paper/2403.19589/) (2024)
- [MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations](https://mlsanity.com/paper/2406.09401/) (2024)
- [Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning](https://mlsanity.com/paper/2309.02999/) (2023)
- [ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes](https://mlsanity.com/paper/2212.06250/) (2022)
- [M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts](https://mlsanity.com/paper/2312.10763/) (2023)
- [RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation](https://mlsanity.com/paper/2312.11829/) (2023)
- [Graph Enhanced Contrastive Learning for Radiology Findings Summarization](https://mlsanity.com/paper/2204.00203/) (2022)
- [Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis](https://mlsanity.com/paper/2210.04208/) (2022)
- [3D Vision and Language Pretraining with Large-Scale Synthetic Data](https://mlsanity.com/paper/2407.06084/) (2024)
- [Contextual Modeling for 3D Dense Captioning on Point Clouds](https://mlsanity.com/paper/2210.03925/) (2022)
- [LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation](https://mlsanity.com/paper/2304.11379/) (2023)
- [CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data](https://mlsanity.com/paper/2310.18773/) (2023)
- [2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision](https://mlsanity.com/paper/2310.12817/) (2023)
- [Dense Object Grounding in 3D Scenes](https://mlsanity.com/paper/2309.02224/) (2023)

## Abstract (arXiv)

3D dense captioning aims to describe individual objects by natural language in 3D scenes, where 3D scenes are usually represented as RGB-D scans or point clouds. However, only exploiting single modal information, e.g., point cloud, previous approaches fail to produce faithful descriptions. Though aggregating 2D features into point clouds may be beneficial, it introduces an extra computational burden, especially in inference phases. In this study, we investigate a cross-modal knowledge transfer using Transformer for 3D dense captioning, X-Trans2Cap, to effectively boost the performance of single-modal 3D caption through knowledge distillation using a teacher-student framework. In practice, during the training phase, the teacher network exploits auxiliary 2D modality and guides the student network that only takes point clouds as input through the feature consistency constraints. Owing to the well-designed cross-modal feature fusion module and the feature alignment in the training phase, X-Trans2Cap acquires rich appearance information embedded in 2D images with ease. Thus, a more faithful caption can be generated only using point clouds during the inference. Qualitative and quantitative results confirm that X-Trans2Cap outperforms previous state-of-the-art by a large margin, i.e., about +21 and about +16 absolute CIDEr score on ScanRefer and Nr3D datasets, respectively.