AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Test-Time Prompt Tuning for Zero-Shot Depth Completion

Chanhwi Jeong, Inhwan Bae, Jin-Hwi Park, Hae-Gon Jeon

ICCV 2025 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 6 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
replace least squares scale fitting with test-time fine-tuning on sparse depthUniDepthV2 · IBims-1MAE: 0.113 -> 0.049Improved
replace fine-tuning with pixelwise visual promptUniDepthV2 · DDADMAE: 1.775 -> 1.482Improved
replace fine-tuning with pixelwise visual promptUniDepthV2 · IBims-1RMSE: 0.152 -> 0.161Hurt
replace fine-tuning with pixelwise visual promptUniDepthV2 · KITTIRMSE: 1.329 -> 1.333No clear effect
use pixelwise prompt instead of random patch prompt (ablation)UniDepthV2 · IBims-1MAE: 0.111 -> 0.043Improved
use pixelwise prompt instead of fixed patch prompt (ablation)UniDepthV2 · IBims-1MAE: 0.079 -> 0.043Improved
use pixelwise prompt instead of padding prompt (ablation)UniDepthV2 · IBims-1MAE: 0.050 -> 0.043Improved
use pixelwise prompt instead of full fine-tuning (learnable parameters) (ablation)UniDepthV2 · IBims-1learnable parameters: 100% -> 0.25%Improved
add visual prompt tuning on top of least squares fit (ablation)ZoeDepth · IBims-1MAE: 0.623 -> 0.176Improved
add visual prompt tuning on top of least squares fit (ablation)Metric3dV2 · NYUv2MAE: 0.174 -> 0.069Improved
use visual prompt rather than Marigold-DC under very sparse input (5 samples)Ours-VP · NYUv2 (5 samples)MAE: 0.358 -> 0.138Improved
use visual prompt rather than Marigold-DC under 4 LiDAR channelsOurs-VP · KITTI (4 channels)MAE: 1.669 -> 0.812Improved

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