paper-with-me

Papers

RayRoPE: Projective Ray Positional Encoding for Multi-view Attention

2026-01-21 · Yu Wu, Minsik Jeon, Jen-Hao Rick Chang, Oncel Tuzel, Shubham Tulsiani arxiv

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. We find that prior (absolute or relative) encoding schemes for multi-view attention do not meet these desiderata, and present RayRoPE to address this gap. RayRoPE represents patch positions based on associated rays and computes query-frame projective coordinates to ensure SE(3) invariance. To adapt to scene geometry, RayRoPE predicts (without direct supervision) a per-token depth to obtain its position along the corresponding ray, while also modeling uncertainty and analytically computing the expected positional encoding. We validate our method on the tasks of novel-view synthesis, stereo depth estimation, and feed-forward 3DGS reconstruction. While remaining efficient, RayRoPE consistently improves over alternate position encoding schemes (e.g., 24% relative improvement on LPIPS in RE10K).

📄 PDF Abstract BibTeX arXiv:2601.15275

Code (0)

등록된 구현이 없습니다.

Tasks

Stereo Depth Estimation

Similar Papers 제목 키워드 기반

Cameras as Relative Positional Encoding

2025-07-14 · RuiLong Li, Brent Yi, Junchen Liu, Hang Gao 외

Transformers are increasingly prevalent for multi-view computer vision tasks, where geometric relationships between viewpoints are critical for 3D perception. To leverage these relationships, multi-view transformers must…

Depth EstimationNovel View SynthesisStereo Depth Estimation

CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation

2026-05-13 · Seonghyun Jin, Youngmin Kim, Sunwoo Park, Jong Chul Ye arxiv

Camera-conditioned video generation requires positional encoding that remains reliable under changes in camera motion, lens configuration, and scene structure. However, existing attention-level camera encodings either pr…

Video Generation

DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers

2026-06-30 · Shun Kenney, Teppei Suzuki arxiv

The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry. Recent advancements ha…

Novel View Synthesis

Span-based Semantic Parsing for Compositional Generalization

2020-09-13 · ACL 2021 5 · Jonathan Herzig, Jonathan Berant

Despite the success of sequence-to-sequence (seq2seq) models in semantic parsing, recent work has shown that they fail in compositional generalization, i.e., the ability to generalize to new structures built of component…

Semantic Parsing

Geometry-Aware Rotary Position Embedding for Consistent Video World Model

2026-02-08 · Chendong Xiang, Jiajun Liu, Jintao Zhang, Xiao Yang 외 arxiv

Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial persistence: they fail to maintain stable sc…