~ similar to 2610.23856· 20 results
Xuanyi Liu, Deyi Ji, Liqun Liu, Lanyun Zhu +7 more
CamGeo is a novel framework that improves sparse camera-conditioned image-to-video generation by distilling rich 3D geometric priors into the diffusion backbone, resulting in geometrically consistent…
Yue Peng, Yongzhe Zhao, Artur Habuda, Khuyen Pham +4 more
Proposed G$^3$VLA, a camera-aware geometric module for pretrained vision-language-action models, injecting calibrated structure into visual tokens using intrinsic-conditioned ray embeddings, projectiv…
Noam Rotstein, Yoad Tewel, Chen Tessler, Haggai Maron +4 more
A model that co-generates video and 3D motion for any supplied rig, along with a camera that registers this motion to the scene.
GeM-NR proposes a novel, training-free framework to achieve general multi-view image editing, enabling consistent edits that drastically change both the geometry and appearance of a nonrigid scene.
Jiahao He, Yihua Shao, Zhengkai Zhao, Pan Gao +5 more
The paper presents GrainGS, a dynamic Gaussian framework for scene reconstruction that balances fine-grained motion modeling, structural stability, and compact representation.
Minseok Joo, Dogyun Park, Taehoon Lee, Kyujin Lee +1 more
The paper proposes COVRAG, a depth-based memory retrieval framework that maximizes the coverage of target-view regions to significantly improve long-term geometric consistency in autoregressive long v…
Jiwen Liu, Shujuan Li, Zhixue Fang, Xiaohan Li +7 more
This paper introduces OmniDirector, a framework for cloning camera motion from reference videos, enabling director-level control for multimodal diffusion transformers.
Gaurav Parmar, Zhengqi Li, Richard Zhang, Jun-Yan Zhu +3 more
The paper introduces vid2vid-long, a correspondence-based approach to improve long-range temporal consistency in video-to-video translation.
Chun-Hsiao Yeh, Shengyi Qian, Manchen Wang, Yi Ma +2 more
The paper proposes GASP, a framework that injects fundamental geometric priors directly into Vision-Language Models (VLMs) using ground-truth video geometry, significantly enhancing 3D spatial reasoni…
The paper presents a new method for precise control over spatial transformations in image editing using 3D boxes as structured specifications.
Tianyi Zhang, Ziyang Gong, Zhenjie Yang, Zhe Qian +1 more
The paper proposes OC-VLA++ to improve viewpoint generalization in robotics using geometry-guided paired-view supervision and cross-view action equivariance.
This paper introduces Align4D, a framework for generating coherent video-3D pairs using any-modal input, achieving state-of-the-art quality and consistency in X-to-4D generation.
Woojung Han, Seil Kang, Youngjun Jun, Min-Hung Chen +2 more
The paper proposes PhaseLock, a training-free framework that preserves physical consistency in image-to-video diffusion models by extracting a motion prior from few-step inference.
The paper introduces MetricScenes, a new large-scale, in-the-wild dataset, and demonstrates that fine-tuning existing geometry models on this dataset significantly mitigates the scale-collapse problem…
Yule Liu, Yilong Yang, Jiale Teng, Hanze Jia +10 more
The paper systematically measures the risk of current image-to-3D models generating harmful geometries, finding that these models are effective at reconstruction and existing safeguards are insufficie…