The paper introduces 4DStreamCtrl, a system that unifies camera motion, object trajectories, and depth into a single 3D point‑track representation, enabling joint control, depth editing, and motion transfer in a single forward pass. By mining in‑the‑wild video for 3D motion supervision and encoding it with a lightweight Geometric Motion Head, the authors train a causal streaming student that can generate arbitrarily long videos in just four denoising steps, achieving 20 FPS on a single high‑end GPU for 480p video. This approach outperforms prior camera‑only, 2D, and offline‑3D methods in motion‑control precision while maintaining temporal coherence over hundreds of frames, thereby enabling interactive 4D‑controllable streaming generation for the first time.
By Shiqian Li, Chenguo Lin, Zhiguang Liu, Yu Tang, Jiarong Ou, Rui Chen, Yixin Zhu
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.
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.
By Wentao Zhou, Xuweiyi Chen, Vignesh Rajagopal, Jeffrey Chen, Rohan Chandra, Zezhou Cheng
arXiv:2606. 31919v1 Announce Type: cross Abstract: Zero-shot Object Goal Navigation (ZSON) with RGB-only perception poses a fundamental challenge for embodied agents, as the absence of explicit depth information introduces severe physical uncertainty and semantic-physical misalignment.
By Wenyuan Xie, Shaokai Wu, Yijin Zhou, Yanbiao Ji, Guodong Zhang, Bayram Bayramli, Qiuchang Li, Xunchu Zhou, Yue Ding, Hongtao Lu
arXiv:2608.29003v1 Announce Type: cross
Abstract: In dynamic and unstructured environments, conventional SLAM systems generally suffer from significant accuracy degeneration due to their static assum...
By Wenting Wang, Jiaxin Guo, Wenzhen Dong, Yun-Hui Liu, Charlie C. L. Wang, Yeung Yam
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
arXiv:2610.01286v1 Announce Type: new
Abstract: Recent depth foundation models like Depth Anything 3 (DA3) achieve remarkable multi-view depth estimation but assume static 3D scenes, limiting their a...
By Xinhao Xiang, Weiyang Li, Zhijie Zheng, Abhijeet Rastogi, Jiawei Zhang
arXiv:2605.25059v4 Announce Type: replace
Abstract: Crucial for autonomous exploration, online 3D occupancy prediction and mapping incrementally construct dense spatial representations on the fly. Em...
By Ruoyu Wang, Yong Liu, Jiahan Li, Sheng Tao, Yuhang Lin, Yukai Ma
arXiv:2610.01742v1 Announce Type: cross
Abstract: Equipping artificial agents with spatial intelligence requires a comprehensive generative prior over the dynamic 3D world. We propose World Motion Mo...
By Jiahui Lei, Qianqian Wang, Trevor Darrell, Angjoo Kanazawa
DiffWAM is a geometry‑conditioned navigation world‑action model that transforms predictive features from a frozen video foundation model into continuous camera trajectories, eliminating the need for future‑video synthesis and multi‑frame reconstruction during deployment. Its Grid‑Motion module preserves spatial‑temporal motion associations, while Latent2Pose grounds them with first‑frame geometry to recover metrically meaningful 3D motion. The system, complemented by FastDreamer for asynchronous trajectory handoff, achieves a trajectory RMSE of 0.3492 m and a 74.40 % endpoint success rate on the DiffWAM‑1000 benchmark, with real‑world tests showing complex UAV behaviors and an onboard implementation reaching 1.08 s latency on NVIDIA Jetson AGX Thor.
By Mo Zhu, Yuze Wu, Xijie Huang, Xiao Cui, Fei Gao, Xin Zhou
GaussianDS introduces a depth‑supervised framework for 3D Gaussian Splatting that jointly optimizes RGB appearance, depth, and compact semantics from scratch. By arranging multi‑view images into a pose‑aware pseudo‑video and propagating view‑consistent masks via SAM2, the method aligns semantic lifting with geometric cues, using depth supervision and edge‑aware refinement to curb semantic drift and boundary leakage. The approach achieves state‑of‑the‑art performance on LERF and 3D‑OVS benchmarks while preserving high‑fidelity reconstruction and enabling downstream tasks such as 3D object removal.
By Yufei Zhang, Chenlu Zhan, Hongwei Wang
Despite rapid progress in interactive world models (IWMs), existing benchmarks evaluate action following only at trajectory level and ignore memory and interaction physics. We introduce WorldOdysseyBench, an open-world benchmark for long-horizon stability across four dimensions, each with tailored innovations: (i) Action: per-frame action metric bypassing cross-model semantic scale disparity and exposing failures hidden by trajectory; (ii) Vision: segment-based drift metric capturing non-monotonic mid-sequence collapse missed by start-vs-end comparisons; (iii) Physics: controllability-gated evaluation over mechanics, optics, and 3D consistency, scoring plausibility under faithful action execution; (iv) Memory: action-decoupled protocol evaluating scene memory via transition-localized 3D point-cloud reconstruction and subject memory via tracking-plus-VLM reasoning.