9 citations · 15 across the 15 of their papers we have counts for
17 papers
MoSE3: Learning World-Space SE(3) at Every Pixel
Jiahuan Cheng, Zhiyi Li, Tian Xia +3
Dense 3D point tracking has been a prominent paradigm for modeling motion in dynamic scenes, but a point track is just a 3-DoF translation curve per pixel: it captures where pixels…
Honeycomb: Constant-Size Scene Memory Representation for Video World Models
Jack Wei Lun Shi, Kaichen Zhou, Haoyu Chen +6
Video world models require persistent scene memory to maintain consistency during long-horizon video generation. Existing spatial memories accumulate RGB observations or latent fea…
Structured 4D Latent Predictive Model for Robot Planning
Zhiyi Li, Peilin Wu, Xiaoshen Han +2
Video predictive models are emerging as a powerful paradigm in robotics, offering a promising path toward task generalization, long-horizon planning, and flexible decision-making.…
SceneAligner: 3D-Grounded Floorplan Localization in the Wild
Junhyeong Cho, Ruojin Cai, Hadar Averbuch-Elor
Many public buildings provide floorplans with a "you are here" indicator to help visitors orient themselves. Floorplan localization seeks to computationally replicate this capabili…
Long-tail Internet photo reconstruction
Yuan Li, Yuanbo Xiangli, Hadar Averbuch-Elor +2
Internet photo collections exhibit an extremely long-tailed distribution: a few famous landmarks are densely photographed and easily reconstructed in 3D, while most real-world site…
ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild
Hanyu Chen, Ruojin Cai, Steve Marschner +1
Symmetry detection is a fundamental problem in computer vision, and symmetries serve as powerful priors for downstream tasks. However, existing learning-based methods for detecting…
Emergent Extreme-View Geometry in 3D Foundation Models
Yiwen Zhang, Joseph Tung, Ruojin Cai +2
3D foundation models (3DFMs) have recently transformed 3D vision, enabling joint prediction of depths, poses, and point maps directly from images. Yet their ability to reason under…
Can Generative Video Models Help Pose Estimation?
Ruojin Cai, Jason Y. Zhang, Philipp Henzler +3
Pairwise pose estimation from images with little or no overlap is an open challenge in computer vision. Existing methods, even those trained on large-scale datasets, struggle in th…
Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features
Yuanbo Xiangli, Ruojin Cai, Hanyu Chen +2
Accurate 3D reconstruction is frequently hindered by visual aliasing, where visually similar but distinct surfaces (aka, doppelgangers), are incorrectly matched. These spurious mat…
Extreme Rotation Estimation in the Wild
Hana Bezalel, Dotan Ankri, Ruojin Cai +1
We present a technique and benchmark dataset for estimating the relative 3D orientation between a pair of Internet images captured in an extreme setting, where the images have limi…
MegaScenes: Scene-Level View Synthesis at Scale
Joseph Tung, Gene Chou, Ruojin Cai +5
Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. Recently, pose-conditioned diffusion models have led to significant progress by extr…
Doppelgangers: Learning to Disambiguate Images of Similar Structures
Ruojin Cai, Joseph Tung, Qianqian Wang +3
We consider the visual disambiguation task of determining whether a pair of visually similar images depict the same or distinct 3D surfaces (e.g., the same or opposite sides of a s…
Neural Scene Chronology
Haotong Lin, Qianqian Wang, Ruojin Cai +4
In this work, we aim to reconstruct a time-varying 3D model, capable of rendering photo-realistic renderings with independent control of viewpoint, illumination, and time, from Int…
Tracking Everything Everywhere All at Once
Qianqian Wang, Yen-Yu Chang, Ruojin Cai +4
We present a new test-time optimization method for estimating dense and long-range motion from a video sequence. Prior optical flow or particle video tracking algorithms typically…
CondenseNet V2: Sparse Feature Reactivation for Deep Networks
Le Yang, Haojun Jiang, Ruojin Cai +4
Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency. The recent proposed CondenseNet has shown that this mecha…
Extreme Rotation Estimation using Dense Correlation Volumes
Ruojin Cai, Bharath Hariharan, Noah Snavely +1
We present a technique for estimating the relative 3D rotation of an RGB image pair in an extreme setting, where the images have little or no overlap. We observe that, even when im…
Learning Gradient Fields for Shape Generation
Ruojin Cai, Guandao Yang, Hadar Averbuch-Elor +4
In this work, we propose a novel technique to generate shapes from point cloud data. A point cloud can be viewed as samples from a distribution of 3D points whose density is concen…