← Back to all news
arXiv Computer Vision By Shuo Zhang, Xin Su, Wei Wang, Jun Liu, Xinrui Zeng, Yongsen Chen, Chenjie Wang, Guibo Zhu, Jinqiao Wang, Bin Luo, Liangpei Zhang

G-ray: Ray-Level Relative Geometric Position Encoding in Multi-View Vision Transformers under Camera Heterogeneity

Read the original on arXiv Computer Vision →

The paper introduces G-ray, a ray-level relative position encoding for multi-view vision Transformers that remains consistent across different camera projections. By parameterizing rotary phases with camera-local ray angles, G-ray achieves projection-invariant positional consistency and can be integrated with existing encodings without extra learned parameters. Experiments on 3D reconstruction and novel-view synthesis benchmarks show that G-ray improves performance, notably reducing mean pointmap relative error by 45.8% over MapAnything.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

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.

By Yu Wu, Minsik Jeon, Jen-Hao Rick Chang, Oncel Tuzel, Shubham Tulsiani
llmscomputer-vision
More like this →
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.

By Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Pascal Fua
llmsragcomputer-visionbenchmarks
More like this →