Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking

arXiv:2608.09613 · cs.CV · Submitted 2026-08-10 · Read on arXiv

cs.CV

Submitted: 2026-08-10

Updated: 2026-10-10

Comments: Accepted by NeurIPS 2026 main track

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Flow Matching — 2× in this paper · explained in 10 episodes
• Optimal Transport — 2× in this paper · explained in 5 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Flow Matching (FM) — 1× in this paper · explained in 2 episodes
• Flow Matching Guided Decoder — 1× in this paper
• Optimal Transport (OT) — 1× in this paper · explained in 5 episodes
• Ordinary Differential Equation — 1× in this paper

Sources

• V-DPM: 4D Video Reconstruction with Dynamic Point Maps
• Trace Anything: Representing Any Video in 4D via Trajectory Fields
• Flow Matching for Generative Modeling
• Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
• Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
• Animate124: Animating One Image to 4D Dynamic Scene
• Make-A-Video: Text-to-Video Generation without Text-Video Data
• Wan: Open and Advanced Large-Scale Video Generative Models
• Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model
• DreamFusion: Text-to-3D using 2D Diffusion
• Choreographing a World of Dynamic Objects
• SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation
• Spatial-Temporal State Propagation Autoregressive Model for 4D Object Generation
• $\pi^3$: Permutation-Equivariant Visual Geometry Learning
• Efficiently Reconstructing Dynamic Scenes One D4RT at a Time
• FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
• Improving and generalizing flow-based generative models with minibatch optimal transport
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

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