Papers › D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding

D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding

2 Dec 2021arXiv:2112.01551archive 2025-07-28

Dave Zhenyu Chen, Qirui Wu, Matthias Nießner, Angel X. Chang

Recent studies on dense captioning and visual grounding in 3D have achieved impressive results. Despite developments in both areas, the limited amount of available 3D vision-language data causes overfitting issues for 3D visual grounding and 3D dense captioning methods. Also, how to discriminatively describe objects in complex 3D environments is not fully studied yet. To address these challenges, we present D3Net, an end-to-end neural speaker-listener architecture that can detect, describe and discriminate. Our D3Net unifies dense captioning and visual grounding in 3D in a self-critical manner. This self-critical property of D3Net also introduces discriminability during object caption generation and enables semi-supervised training on ScanNet data with partially annotated descriptions. Our method outperforms SOTA methods in both tasks on the ScanRefer dataset, surpassing the SOTA 3D dense captioning method by a significant margin.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D dense captioning3D visual groundingCaption GenerationDense CaptioningVisual Grounding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D dense captioning Nr3D D3Net BLEU-4 20.70 #8 of 10 Archive leaderboard report
3D dense captioning Nr3D D3Net CIDEr 33.85 #8 of 10 Archive leaderboard report
3D dense captioning Nr3D D3Net METEOR 23.13 #8 of 10 Archive leaderboard report
3D dense captioning Nr3D D3Net ROUGE-L 53.38 #8 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections