Solv3R: 3D Looped Transformer as a Multi-view Solver
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
Project page: https://ubc-vision.github.io/solv3r
Terminology
Sources
- Layer Normalization
- Virtual KITTI 2
- Geometric Context Transformer for Streaming 3D Reconstruction
- HD-VGGT: High-Resolution Visual Geometry Transformer
- SURE-Map: Self-Correcting Streaming Geometric Foundation Models
- InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
- Scaling Latent Reasoning via Looped Language Models
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