Feature Puzzles: Single-Image Supervision for Multi-View 3D-Aware Segmentation
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Project page: https://featurepuzzles.github.io
Terminology
Sources
- SAB3R: Semantic-Augmented Backbone in 3D Reconstruction
- MV-SAM: Multi-view Promptable Segmentation using Pointmap Guidance
- Depth Anything 3: Recovering the Visual Space from Any Views
- RobotPan: A 360$^\circ$ Surround-View Robotic Vision System for Embodied Perception
- SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
- DINOv3
- VGGT-
- MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
- S4VY: Segment Anything in Feed-Forward 4D Visual Geometry
- MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction
- Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models
- IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer
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