4 citations · 7 across the 25 of their papers we have counts for
28 papers
Native Video-Action Pretraining for Generalizable Robot Control
Qihang Zhang, Lin Li, Luyao Zhang +26
The advent of video-action models offers a promising path for robot control. Nevertheless, we argue that repurposing video generative models designed for digital content creation i…
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Shuailei Ma, Jiaqi Liao, Xinyang Wang +24
Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their primary focus on content creation. For example, their design inheren…
From Foundation to Application: Improving VLA Models in Practice
Wei Wu, Fangjing Wang, Fan Lu +21
Despite recent progress of VLA foundation models, the disparity between laboratory conditions and real-world applications continues to impede their practical implementation. To bri…
Vision Pretraining for Dense Spatial Perception
Zelin Fu, Bin Tan, Changjiang Sun +6
Dense spatial perception is essential for physical intelligence, where visual systems are expected to recover structured, metric, and actionable representations from pixel observat…
AetheRock: An Arm-Worn Robot Teaching System for Force-Guided Vision-Tactile Learning
Hong Li, Yue Xu, Yihan Tang +8
Force and tactile sensing are indispensable in contact-rich manipulation. However, force-aware robot learning faces critical challenges due to the incompatible assembly of tactile…
Tac-DINO: Learning Vision-Tactile Features with Patch Alignment
Hong Li, Yankang Dong, Yue Xu +8
Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or alignment. However, tactile…
LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
Lin-Zhuo Chen, Jian Gao, Shangzhan Zhang +9
Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric accuracy, temporal consistency,…
Interacted Planes Reveal 3D Line Mapping
Zeran Ke, Bin Tan, Gui-Song Xia +2
3D line mapping from multi-view RGB images provides a compact and structured visual representation of scenes. We study the problem from a physical and topological perspective: a 3D…
Masked Depth Modeling for Spatial Perception
Bin Tan, Changjiang Sun, Xiage Qin +8
Spatial visual perception is a fundamental requirement in physical-world applications like autonomous driving and robotic manipulation, driven by the need to interact with 3D envir…
FlowSSC: Universal Generative Monocular Semantic Scene Completion via One-Step Latent Diffusion
Zichen Xi, Hao-Xiang Chen, Nan Xue +5
Semantic Scene Completion (SSC) from monocular RGB images is a fundamental yet challenging task due to the inherent ambiguity of inferring occluded 3D geometry from a single view.…
Causal World Modeling for Robot Control
Lin Li, Qihang Zhang, Yiming Luo +9
This work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively, video world…
Real-Time 3D Object Detection with Inference-Aligned Learning
Chenyu Zhao, Xianwei Zheng, Zimin Xia +2
Real-time 3D object detection from point clouds is essential for dynamic scene understanding in applications such as augmented reality, robotics and navigation. We introduce a nove…
PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting
Changkun Liu, Bin Tan, Zeran Ke +6
This paper addresses metric 3D reconstruction of indoor scenes by exploiting their inherent geometric regularities with compact representations. Using planar 3D primitives - a well…
UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANs
Mengfei Xia, Nan Xue, Jiapeng Zhu +1
Adversarial training turns out to be the key to one-step generation, especially for Generative Adversarial Network (GAN) and diffusion model distillation. Yet in practice, GAN trai…
SpatialTrackerV2: 3D Point Tracking Made Easy
Yuxi Xiao, Jianyuan Wang, Nan Xue +7
We present SpatialTrackerV2, a feed-forward 3D point tracking method for monocular videos. Going beyond modular pipelines built on off-the-shelf components for 3D tracking, our app…
ScaleLSD: Scalable Deep Line Segment Detection Streamlined
Zeran Ke, Bin Tan, Xianwei Zheng +3
This paper studies the problem of Line Segment Detection (LSD) for the characterization of line geometry in images, with the aim of learning a domain-agnostic robust LSD model that…
Equivariant Flow Matching for Point Cloud Assembly
Ziming Wang, Nan Xue, Rebecka Jörnsten
The goal of point cloud assembly is to reconstruct a complete 3D shape by aligning multiple point cloud pieces. This work presents a novel equivariant solver for assembly tasks bas…
Seeing through Satellite Images at Street Views
Ming Qian, Bin Tan, Qiuyu Wang +5
This paper studies the task of SatStreet-view synthesis, which aims to render photorealistic street-view panorama images and videos given any satellite image and specified camera p…
FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views
Shangzhan Zhang, Jianyuan Wang, Yinghao Xu +5
We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a cha…
PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes
Bin Tan, Rui Yu, Yujun Shen +1
This paper presents PlanarSplatting, an ultra-fast and accurate surface reconstruction approach for multiview indoor images. We take the 3D planes as the main objective due to thei…
Rectified Diffusion Guidance for Conditional Generation
Mengfei Xia, Nan Xue, Yujun Shen +3
Classifier-Free Guidance (CFG), which combines the conditional and unconditional score functions with two coefficients summing to one, serves as a practical technique for diffusion…
Stratified Avatar Generation from Sparse Observations
Han Feng, Wenchao Ma, Quankai Gao +3
Estimating 3D full-body avatars from AR/VR devices is essential for creating immersive experiences in AR/VR applications. This task is challenging due to the limited input from Hea…
A Pixel Is Worth More Than One 3D Gaussians in Single-View 3D Reconstruction
Jianghao Shen, Nan Xue, Tianfu Wu
Learning 3D scene representation from a single-view image is a long-standing fundamental problem in computer vision, with the inherent ambiguity in predicting contents unseen from…
Multi-View Attentive Contextualization for Multi-View 3D Object Detection
Xianpeng Liu, Ce Zheng, Ming Qian +5
We present Multi-View Attentive Contextualization (MvACon), a simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detectio…