AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

3D Reconstruction from Transient Measurements with Time-Resolved Transformer

Yue Li, Shida Sun, Hong Wu Yu, Feng Ying Xu, Zhiwei Xiong

TPAMI 2026 · Architectures and efficiency › Attention and transformers · approach: Efficient image transformers · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add TV regularization loss (ablation)TRT-LOS · Simulated LOS (SBR X:2 avg)depth RMSE: 0.0370 -> 0.0361Improved
add TV regularization loss (ablation)TRT-LOS · Simulated LOS (SBR Y:100 avg)depth RMSE: 0.0876 -> 0.0813Improved
add deep local features to global-only fusion (ablation)TRT-LOS · Simulated LOS (SBR X:2 avg)depth RMSE: 4.7183 -> 0.0361Improved
add deep global features to local-only fusion (ablation)TRT-LOS · Simulated LOS (SBR X:2 avg)depth RMSE: 0.0389 -> 0.0361Improved
add temporal attention to spatial-only attention (ablation)TRT-LOS · Simulated LOS (SBR X:2 avg)depth RMSE: 0.0994 -> 0.0361Improved
add spatial attention to temporal-only attention (ablation)TRT-LOS · Simulated LOS (SBR X:2 avg)depth RMSE: 0.0392 -> 0.0361Improved
add local-global integration (LGInt) in cross attention decoder (ablation)TRT-LOS · Simulated LOS (SBR Y:100 avg)depth RMSE: 0.0892 -> 0.0813Improved
increase TRT blocks from 12 to 24 (ablation)TRT-LOS · Simulated LOS (SBR X:50 avg)depth RMSE: 0.0508 -> 0.0540Hurt
increase TRT blocks from 12 to 24 (ablation)TRT-LOS · Simulated LOS (SBR X:2 avg)depth RMSE: 0.0361 -> 0.0360No clear effect
increase TRT input channels from 64 to 128 (ablation)TRT-LOS · Simulated LOS (SBR X:2 avg)depth RMSE: 0.0361 -> 0.0374Hurt
add local-global integration (LGInt) in cross attention decoder (ablation)TRT-NLOS · Simulated NLOS Seendepth RMSE: 0.0904 -> 0.0849Improved
add temporal attention to spatial-only attention (ablation)TRT-NLOS · Simulated NLOS Seendepth RMSE: 0.0877 -> 0.0849Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy