Dyna3: VLM-Guided Training-Free 4D Reconstruction via Depth Foundation Models

arXiv:2610.01286 · cs.CV · Submitted 2026-10-01 · Read on arXiv

cs.CV

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• Accuracy — 20× in this paper · explained in 1 episode
• Consistency — 11× in this paper · explained in 3 episodes
• Point Clouds — 6× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Foundation Model — 5× in this paper · explained in 3 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• International Conference on Computer Vision — 4× in this paper
• Foundation Models — 3× in this paper · explained in 7 episodes
• Gaussian Splatting — 3× in this paper · explained in 4 episodes
• Instance Segmentation — 3× in this paper · explained in 3 episodes
• Relative Translation Error — 3× in this paper
• Training-Free Framework — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Optical Flow — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Absolute Trajectory Error — 1× in this paper
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• In European Conference on Computer Vision — 1× in this paper
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Relative Rotation Error — 1× in this paper
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• SAM 3: Segment Anything with Concepts
• Easi3R: Estimating Disentangled Motion from DUSt3R Without Training
• VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction
• Depth Anything 3: Recovering the Visual Space from Any Views
• DINOv2: Learning Robust Visual Features without Supervision
• Enhancing Blind Video Quality Assessment with Rich Quality-aware Features
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• Shape of Motion: 4D Reconstruction from a Single Video
• Are AI-Generated Driving Videos Ready for Autonomous Driving? A Diagnostic Evaluation Framework
• DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction
• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
• PRISM: Feed-Forward Single-Image 3D Reconstruction via Geometric Warp-Residual Modeling
• TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction
• Open3D: A Modern Library for 3D Data Processing

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