RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory

arXiv:2609.23286 · cs.CV · Submitted 2026-09-20 · Read on arXiv

cs.CV

Submitted: 2026-09-20

Updated: 2026-09-20

Code: https://github.com/amao996/RegVGGT

Terminology

• Accuracy — 17× in this paper · explained in 1 episode
• Transformer — 15× in this paper · explained in 2 episodes
• Consistency — 10× in this paper · explained in 3 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Ablation study — 4× in this paper · explained in 1 episode
• Decoupling — 4× in this paper · explained in 2 episodes
• KV cache — 4× in this paper · explained in 3 episodes
• Temporal consistency — 4× in this paper · explained in 2 episodes
• Anchor Tokens — 3× in this paper · explained in 1 episode
• Computational overhead — 3× in this paper · explained in 2 episodes
• Generalizability — 3× in this paper · explained in 6 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Visual Geometry Grounded Transformer — 3× in this paper
• Alignment — 2× in this paper · explained in 1 episode
• Gaussian Splatting — 2× in this paper · explained in 4 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• 3D Gaussian Splatting — 1× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Absolute Trajectory Error — 1× in this paper
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Normal Consistency — 1× in this paper
• Sparse Attention — 1× in this paper · explained in 5 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• TTT3R: 3D Reconstruction as Test-Time Training
• ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
• FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• $\textit{S}^3$Gaussian: Self-Supervised Street Gaussians for Autonomous Driving
• MapAnything: Universal Feed-Forward Metric 3D Reconstruction
• STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
• WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
• Robust Incremental Structure-from-Motion with Hybrid Features
• Evict3R: Training-Free Token Eviction for Memory-Bounded Streaming Visual Geometry Transformers
• DINOv2: Learning Robust Visual Features without Supervision
• FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
• XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
• Attention Is All You Need
• 3D Reconstruction with Spatial Memory
• $\pi^3$: Permutation-Equivariant Visual Geometry Learning
• Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
• EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding
• InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams

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