StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion

arXiv:2603.01765 · cs.CV · Submitted 2026-03-02 · Read on arXiv

cs.CV

Submitted: 2026-03-02

Updated: 2026-09-22

Project page: https://wonjun-lee1009.github.io/EffTTO-Depth-Completion

Terminology

• Adaptation — 72× in this paper · explained in 1 episode
• Test-Time Optimization — 44× in this paper
• Foundation Model — 23× in this paper · explained in 3 episodes
• Foundation Models — 17× in this paper · explained in 7 episodes
• Accuracy — 14× in this paper · explained in 1 episode
• Alignment — 13× in this paper · explained in 1 episode
• Generalization — 9× in this paper · explained in 13 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Sparsity — 7× in this paper · explained in 4 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Ablation study — 4× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Domain Shift — 2× in this paper · explained in 4 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Korea Advanced Institute of Science and Technology — 1× in this paper
• LoRA Adaptation — 1× in this paper · explained in 2 episodes
• Mean Absolute Error — 1× in this paper
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Parameter Efficiency — 1× in this paper · explained in 3 episodes
• Root Mean Squared Error — 1× in this paper
• Self-Supervised Learning — 1× in this paper · explained in 7 episodes

Sources

• MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
• Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
• Structure-Aware Residual Pyramid Network for Monocular Depth Estimation
• From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
• Depth Anything 3: Recovering the Visual Space from Any Views
• DepthLab: From Partial to Complete
• Towards Stable Test-Time Adaptation in Dynamic Wild World
• UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler
• AnyDepth: Depth Estimation Made Easy
• Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling
• DINOv3
• NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models