跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-10AI 評分39

OmniCam:透過以幾何為基礎的姿態 token 學習生成全向相機軌跡

OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning

AI 導讀

OmniCam 是一款自回歸模型,可根據單張全景圖和文字描述生成相機姿態序列,透過幾何與目標感知條件提升軌跡準確度並減少碰撞。研究團隊構建了包含 267,700 條軌跡的 OmniCaT;在其評測中,與在 OmniCaT 上重新訓練的 GenDoP 相比,OmniCam 的軌跡誤差降低 28–47%,碰撞率降低 65.8%。

正文

Published on Oct 10

Authors:

,

,

,

,

,

,

Abstract

OmniCam is an autoregressive model that generates camera pose sequences from panoramas and text, using geometric and target-aware conditioning to improve trajectory accuracy and reduce collisions.

Camera trajectories control viewpoint changes in video generation, scene reconstruction, and robotic perception. Generating them from language requires both scene geometry and target-aware framing. We introduce OmniCam, an autoregressive model that generates camera pose sequences from a single panorama and textual trajectory descriptions. Its geometry-grounded pose token learning combines three components: a panoramic point-cloud encoder for omnidirectional geometric context; hybrid absolute-rotation and relative-translation tokenization with temporally consistent quaternion signs; and separate geometric and semantic conditioning streams with an explicit 3D target anchor. We also construct OmniCaT, containing 267,700 trajectories across four camera behaviors. On the reported OmniCaT evaluation, OmniCam reduces trajectory errors by 28--47% and collision rate by 65.8% relative to GenDoP retrained on OmniCaT. Against the best baseline for each metric, the ATE and collision reductions are 43.0% and 62.3%, respectively. Component ablations support the use of geometric and target-aware conditioning, while downstream experiments examine camera-controlled video generation and robotic active perception.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.09513

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.09513 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.09513 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.09513 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co