arXiv Computer Vision

Stereo4DWalker: Learning 4D-aware Embodied Urban Navigation from Internet Stereo Videos

Stereo4DWalker is a 4D-aware embodied navigation model that uses stereo video inputs to explicitly construct structured representations of geometry and motion. These 4D structures are incorporated into a navigation transformer via 4D-conditioned attention layers, enabling the agent to learn robust urban navigation. The authors also curate a large-scale stereo navigation dataset with automatically annotated actions from Internet stereo videos, and demonstrate that Stereo4DWalker outperforms state‑of‑the‑art methods while requiring only 1.5% of the training data.

arXiv Computer Vision
Sep 1

CL4D: Contrastive Language-4D Pretraining for Vision-Language Reasoning in Dynamic Scenes

arXiv:2608.18734v2 Announce Type: replace Abstract: 4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vis...

By Kumal Hewagamage, Isuranga Senavirathne, Sasika Amarasinghe, Hasitha Gallella, Dulanga Weerakoon, Vigneshwaran Subbaraju, Ranga Rodrigo
Hugging Face Trending Papers
Jul 21

IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer

Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding.

Hugging Face Trending Papers
Oct 15

Gen4P: Video Generators are 4D Perceivers

Gen4P is a unified framework that transforms a pretrained video generator into a feed‑forward 4D perceiver, enabling recovery of 4D geometry and motion from monocular video without iterative denoising. It processes clean video latents in a single encoder pass and uses a lightweight cross‑attention decoder to predict requested 4D attributes, supporting flexible spatial sampling and continuous‑time queries for temporal flexibility. By incorporating a frozen pretrained video‑depth LoRA as a geometry prior, Gen4P improves performance on 3D point tracking, video depth, and camera pose estimation, achieving state‑of‑the‑art or competitive results on these tasks and demonstrating robust tracking of complex motion in in‑the‑wild videos.

arXiv Computer Vision
Sep 11

Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation

Dream4D is a new framework for generating spatiotemporally coherent 4D content. It uses a two‑stage pipeline: first, few‑shot learning predicts optimal camera trajectories from a single image; second, a pose‑conditioned diffusion process creates geometrically consistent multi‑view sequences that are converted into a persistent 4D representation. The method uniquely combines rich temporal priors from video diffusion models with geometric awareness from reconstruction models, achieving higher quality metrics such as mPSNR and mSSIM compared to existing approaches.

By Xiaoyan Liu, Kangrui Li, Jiaxin Liu, Yuehao Song, Yujie Xing
arXiv Computer Vision
Oct 16

Gen4P: Video Generators are 4D Perceivers

Gen4P is a unified framework that transforms a pretrained video generator into a feed‑forward 4D perceiver, enabling recovery of 4D geometry and motion from monocular video without iterative denoising. It processes video latents in a single encoder pass and uses a lightweight cross‑attention decoder to predict requested 4D attributes, supporting flexible spatial sampling and continuous‑time queries. By integrating a frozen video‑depth LoRA as a geometry prior, Gen4P improves performance on 3D point tracking, video depth, and camera pose estimation, achieving state‑of‑the‑art or competitive results on benchmark tasks and demonstrating robust tracking of complex motion in in‑the‑wild videos.

By Yitong Xia, Zeren Jiang, Chuanxia Zheng
arXiv Computer Vision
Oct 1

XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments

arXiv:2604.18484v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models drive next-generation autonomous systems, but training them requires scalable, high-quality annotations from co...

By Kangan Qian, ChuChu Xie, Yang Zhong, Jingrui Pang, Siwen Jiao, Sicong Jiang, Zilin Huang, Yunlong Wang, Kun Jiang, Mengmeng Yang, Hao Ye, Guanghao Zhang, Hangjun Ye, Guang Chen, Long Chen, Diange Yang
arXiv AI
Nov 6

OpenNWM: A Generalist Navigation World Model with Latent Action Pretraining

OpenNWM is a generalist navigation world model that learns universal latent actions from large-scale action‑free videos and aligns them with physical motions through action‑conditioned post‑training. The authors curate NavAnywhere, a dataset of 17.5 million visual observations from 15 heterogeneous sources, covering diverse viewpoints and motion patterns across five scene types. Experiments show that latent‑action pretraining improves visual prediction and navigation performance both in‑domain and out‑of‑domain.

By Dujun Nie, Ruiqi Song, Zixuan Wang, Hanqing Wang, Yifan Han, Baiyong Ding, Wenzhao Zheng, Hangbin Wu, Long Chen
arXiv AI
Jun 30

Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation

arXiv:2606. 29908v1 Announce Type: cross Abstract: Existing world model-based planners for visual navigation typically follow a verification-centric paradigm, decoupling goal intent from trajectory synthesis.

By Hong Chen, Daqi Liu, Zehan Zhang, Haiguang Wang, Tianhao Lu, Longfei Yan, Haiyang Sun, Fangzhen Li, Hongwei Xie, Bing Wang, Guang Chen, Hangjun Ye, Yihua Tan
arXiv Computer Vision
Sep 16

GeoLAM: Learning Geometry-Grounded Latent Actions from Unlabeled Human Videos

GeoLAM is a framework that learns geometry‑grounded latent actions from unlabeled human videos. It uses future‑frame reconstruction with a frozen geometric feature hierarchy and motion supervision from a 4D geometry teacher to capture 3D displacement, image‑plane motion, and surface‑orientation changes. After pretraining, the representation serves as transition targets for a world‑action model trained on robot demonstrations, enabling denoised latent actions and executable action chunks without requiring hand‑pose annotations or future‑video generation during deployment.

By Yifan Xie, Hekun Tian, Jinkun Liu, YuAn Wang, Qiao Sun, Wenbo Ding