arXiv AI
WorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 10
CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation
arXiv:2605.12938v2 Announce Type: replace-cross Abstract: Video world models should predict future appearance in a way that remains consistent with 3D scene structure, camera motion, and lens geometr...
arXiv Machine Learning
Jul 8
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
arXiv:2601. 15275v3 Announce Type: replace-cross Abstract: We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-invariant attention with multi-frequency similarity, and can adapt to the geometry of the underlying 3D scene.
arXiv Computer Vision
4d ago
HRoPE: Homography Relative Positional Encoding
arXiv:2610.28284v1 Announce Type: new Abstract: Geometric Relative Positional Encoding has become the primary mechanism for injecting spatial inductive biases into multi-view transformers. Existing d...
arXiv Computer Vision
Sep 22
Revisiting Multi-View Stereo: A Sequence-to-Sequence Formulation
The paper proposes a new sequence-to-sequence formulation for multi-view stereo (MVS) that jointly predicts 3D geometry for all input views using a global transformer architecture. It introduces ray‑map embeddings to inject camera parameters into image tokens and a unified global cost volume to capture 3D structure across all views. Experiments on public benchmarks demonstrate state‑of‑the‑art performance, outperforming both traditional MVS and feed‑forward reconstruction baselines.
arXiv AI
Jul 13
MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs
arXiv:2607. 08970v1 Announce Type: cross Abstract: Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model.
arXiv AI
Oct 16
GeoState: Learning View-Decoupled Geometry States for 3D World Modeling
GeoState introduces a view‑decoupled geometry representation for predictive 3D world modeling, separating scene‑state evolution from camera‑dependent observation. It aggregates multi‑view geometry foundation model features into a scene tokenizer, then uses a geometry decoder to query this state with camera rays. An autoregressive world model predicts future scene states while modeling camera motion independently, enabling consistent decoding under any camera and maintaining a single context‑derived scale throughout rollouts.