Papers › Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help...
Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World
Jiaming Zhang, Kailun Yang, Angela Constantinescu, Kunyu Peng, Karin Müller, Rainer Stiefelhagen
Common fully glazed facades and transparent objects present architectural barriers and impede the mobility of people with low vision or blindness, for instance, a path detected behind a glass door is inaccessible unless it is correctly perceived and reacted. However, segmenting these safety-critical objects is rarely covered by conventional assistive technologies. To tackle this issue, we construct a wearable system with a novel dual-head Transformer for Transparency (Trans4Trans) model, which is capable of segmenting general and transparent objects and performing real-time wayfinding to assist people walking alone more safely. Especially, both decoders created by our proposed Transformer Parsing Module (TPM) enable effective joint learning from different datasets. Besides, the efficient Trans4Trans model composed of symmetric transformer-based encoder and decoder, requires little computational expenses and is readily deployed on portable GPUs. Our Trans4Trans model outperforms state-of-the-art methods on the test sets of Stanford2D3D and Trans10K-v2 datasets and obtains mIoU of 45.13% and 75.14%, respectively. Through various pre-tests and a user study conducted in indoor and outdoor scenarios, the usability and reliability of our assistive system have been extensively verified.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semantic Segmentation | EventScape | Trans4Trans | mIoU | 51.86 | #7 of 12 | Archive leaderboard | report |
| Semantic Segmentation | Trans10K | Trans4Trans (M) | GFLOPs | 34.38 | #1 of 15 | Archive leaderboard | report |
| Semantic Segmentation | Trans10K | Trans4Trans (M) | mIoU | 75.14% | #1 of 15 | Archive leaderboard | report |
| Semantic Segmentation | Trans10K | Trans4Trans (S) | GFLOPs | 19.92 | #2 of 15 | Archive leaderboard | report |
| Semantic Segmentation | Trans10K | Trans4Trans (S) | mIoU | 74.15% | #2 of 15 | Archive leaderboard | report |
| Semantic Segmentation | Trans10K | Trans4Trans (T) | GFLOPs | 10.45 | #7 of 15 | Archive leaderboard | report |
| Semantic Segmentation | Trans10K | Trans4Trans (T) | mIoU | 68.63% | #7 of 15 | 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.
Methods
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