</> Code with Papers by Syntology

Papers › TR3D: Towards Real-Time Indoor 3D Object Detection

TR3D: Towards Real-Time Indoor 3D Object Detection

6 Feb 2023arXiv:2302.02858archive 2025-07-28

Danila Rukhovich, Anna Vorontsova, Anton Konushin

Recently, sparse 3D convolutions have changed 3D object detection. Performing on par with the voting-based approaches, 3D CNNs are memory-efficient and scale to large scenes better. However, there is still room for improvement. With a conscious, practice-oriented approach to problem-solving, we analyze the performance of such methods and localize the weaknesses. Applying modifications that resolve the found issues one by one, we end up with TR3D: a fast fully-convolutional 3D object detection model trained end-to-end, that achieves state-of-the-art results on the standard benchmarks, ScanNet v2, SUN RGB-D, and S3DIS. Moreover, to take advantage of both point cloud and RGB inputs, we introduce an early fusion of 2D and 3D features. We employ our fusion module to make conventional 3D object detection methods multimodal and demonstrate an impressive boost in performance. Our model with early feature fusion, which we refer to as TR3D+FF, outperforms existing 3D object detection approaches on the SUN RGB-D dataset. Overall, besides being accurate, both TR3D and TR3D+FF models are lightweight, memory-efficient, and fast, thereby marking another milestone on the way toward real-time 3D object detection. Code is available at https://github.com/SamsungLabs/tr3d .

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 Object DetectionObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection 3RScan TR3D mAP@0.25 62.3 #2 of 3 Archive leaderboard report
3D Object Detection 3RScan TR3D mAP@0.5 45.4 #2 of 3 Archive leaderboard report
3D Object Detection MultiScan TR3D mAP@0.25 56.7 #2 of 3 Archive leaderboard report
3D Object Detection MultiScan TR3D mAP@0.5 42.3 #2 of 3 Archive leaderboard report
3D Object Detection S3DIS TR3D mAP@0.25 74.5 #4 of 7 Archive leaderboard report
3D Object Detection S3DIS TR3D mAP@0.5 51.7 #4 of 7 Archive leaderboard report
3D Object Detection SUN-RGBD val TR3D+FF mAP@0.25 69.4 #2 of 32 Archive leaderboard report
3D Object Detection SUN-RGBD val TR3D+FF mAP@0.5 53.4 #2 of 32 Archive leaderboard report
3D Object Detection SUN-RGBD val TR3D (Geo only) mAP@0.25 67.1 #7 of 32 Archive leaderboard report
3D Object Detection SUN-RGBD val TR3D (Geo only) mAP@0.5 50.4 #7 of 32 Archive leaderboard report
3D Object Detection ScanNet++ TR3D mAP@0.25 26.2 #2 of 3 Archive leaderboard report
3D Object Detection ScanNet++ TR3D mAP@0.5 14.5 #2 of 3 Archive leaderboard report
3D Object Detection ScanNetV2 TR3D mAP@0.25 72.9 #14 of 33 Archive leaderboard report
3D Object Detection ScanNetV2 TR3D mAP@0.5 59.3 #14 of 33 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