HIST3R: Decomposing and Rectifying State Updates with History for Streaming 3D Reconstruction
cs.CV
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
- TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction
- FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs