MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting

arXiv:2610.10759 · cs.CV · Submitted 2026-10-07 · Read on arXiv

cs.CV

Submitted: 2026-10-07

Updated: 2026-10-07

Comments: Accepted by NeurIPS 2026. Code will be released at: https://github.com/liujiuming123/Messenger

Code: https://github.com/liujiuming123/Messenger

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

Terminology

• Conference on Computer Vision and Pattern Recognition — 9× in this paper
• Consistency — 8× in this paper · explained in 3 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Optical Flow — 6× in this paper · explained in 2 episodes
• Point Clouds — 5× in this paper · explained in 2 episodes
• World Model — 4× in this paper · explained in 7 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Feature Extraction — 3× in this paper · explained in 2 episodes
• Loss Function — 3× in this paper · explained in 2 episodes
• Temporal consistency — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Computational overhead — 2× in this paper · explained in 2 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• IEEE International Conference on Robotics and Automation — 2× in this paper
• Uncertainty Quantification — 2× in this paper · explained in 8 episodes
• AdamW Optimizer — 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 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Cross-Attention Mechanism — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Pyramid-Warping-Cost Volume — 1× in this paper
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Binding Multiple Modalities via Multimodal Wasserstein Barycenter
• UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
• TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation
• EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy
• RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer
• Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
• Denoising Diffusion Implicit Models
• Wan: Open and Advanced Large-Scale Video Generative Models
• Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
• WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis

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