English
Related papers

Related papers: TrackCraft3R: Repurposing Video Diffusion Transfor…

200 papers

Streaming feed-forward 3D reconstruction enables real-time joint estimation of scene geometry and camera poses from RGB images. However, without explicit dynamic reasoning, streaming models can be affected by moving objects, causing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Feiran Wang , Zezhou Shang , Gaowen Liu , Yan Yan

Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite…

Computer Vision and Pattern Recognition · Computer Science 2022-10-03 Yihong Xu , Yutong Ban , Guillaume Delorme , Chuang Gan , Daniela Rus , Xavier Alameda-Pineda

Realistic scene reconstruction in driving scenarios poses significant challenges due to fast-moving objects. Most existing methods rely on labor-intensive manual labeling of object poses to reconstruct dynamic objects in canonical space and…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Ruida Zhang , Chengxi Li , Chenyangguang Zhang , Xingyu Liu , Haili Yuan , Yanyan Li , Xiangyang Ji , Gim Hee Lee

Recent advancements in multi-view scene reconstruction have been significant, yet existing methods face limitations when processing streams of input images. These methods either rely on time-consuming offline optimization or are restricted…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Zhuoguang Chen , Minghui Qin , Tianyuan Yuan , Zhe Liu , Hang Zhao

Distinguishing visually similar objects by their motion remains a critical challenge in computer vision. Although supervised trackers show promise, contemporary self-supervised trackers struggle when visual cues become ambiguous, limiting…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Chenshuang Zhang , Kang Zhang , Joon Son Chung , In So Kweon , Junmo Kim , Chengzhi Mao

Motion transfer enables controllable video generation by transferring temporal dynamics from a reference video to synthesize a new video conditioned on a target caption. However, existing Diffusion Transformer (DiT)-based methods are…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Samuel Teodoro , Yun Chen , Agus Gunawan , Soo Ye Kim , Jihyong Oh , Munchurl Kim

Recent advancements in 3D Gaussian Splatting (3DGS) have demonstrated its potential for efficient and photorealistic 3D reconstructions, which is crucial for diverse applications such as robotics and immersive media. However, current…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Daheng Yin , Isaac Ding , Yili Jin , Jianxin Shi , Jiangchuan Liu

Robust object tracking requires knowledge and understanding of the object being tracked: its appearance, its motion, and how it changes over time. A tracker must be able to modify its underlying model and adapt to new observations. We…

Computer Vision and Pattern Recognition · Computer Science 2018-02-28 Daniel Gordon , Ali Farhadi , Dieter Fox

Although considerable advancements have been attained in self-supervised depth estimation from monocular videos, most existing methods often treat all objects in a video as static entities, which however violates the dynamic nature of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Xiuzhe Wu , Xiaoyang Lyu , Qihao Huang , Yong Liu , Yang Wu , Ying Shan , Xiaojuan Qi

Recent Diffusion Transformers (e.g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is still being determined whether the Transformer architecture performs equally well in 3D shape…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Shentong Mo , Enze Xie , Ruihang Chu , Lewei Yao , Lanqing Hong , Matthias Nießner , Zhenguo Li

We introduce the first data-driven multi-view 3D point tracker, designed to track arbitrary points in dynamic scenes using multiple camera views. Unlike existing monocular trackers, which struggle with depth ambiguities and occlusion, or…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Frano Rajič , Haofei Xu , Marko Mihajlovic , Siyuan Li , Irem Demir , Emircan Gündoğdu , Lei Ke , Sergey Prokudin , Marc Pollefeys , Siyu Tang

We present PAD3R, a method for reconstructing deformable 3D objects from casually captured, unposed monocular videos. Unlike existing approaches, PAD3R handles long video sequences featuring substantial object deformation, large-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Ting-Hsuan Liao , Haowen Liu , Yiran Xu , Songwei Ge , Gengshan Yang , Jia-Bin Huang

We present TraceFlow, a novel framework for high-fidelity rendering of dynamic specular scenes by addressing two key challenges: precise reflection direction estimation and physically accurate reflection modeling. To achieve this, we…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Jiachen Tao , Junyi Wu , Haoxuan Wang , Zongxin Yang , Dawen Cai , Yan Yan

4D video control is essential in video generation as it enables the use of sophisticated lens techniques, such as multi-camera shooting and dolly zoom, which are currently unsupported by existing methods. Training a video Diffusion…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Weikang Bian , Zhaoyang Huang , Xiaoyu Shi , Yijin Li , Fu-Yun Wang , Hongsheng Li

Feed-forward multi-frame 3D reconstruction models often degrade on videos with object motion. Global-reference becomes ambiguous under multiple motions, while the local pointmap relies heavily on estimated relative poses and can drift,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Xingyu Miao , Weiguang Zhao , Tao Lu , Linning Xu , Mulin Yu , Yang Long , Jiangmiao Pang , Junting Dong

Building high-fidelity digital twins of articulated objects from visual data remains a central challenge. Existing approaches depend on multi-view captures of the object in discrete, static states, which severely constrains their real-world…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Lijun Guo , Haoyu Zhao , Xingyue Zhao , Rong Fu , Linghao Zhuang , Siteng Huang , Zhongyu Li , Hua Zou

This paper presents a novel framework for converting 2D videos to immersive stereoscopic 3D, addressing the growing demand for 3D content in immersive experience. Leveraging foundation models as priors, our approach overcomes the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 Sijie Zhao , Wenbo Hu , Xiaodong Cun , Yong Zhang , Xiaoyu Li , Zhe Kong , Xiangjun Gao , Muyao Niu , Ying Shan

We present MotionCrafter, a framework that leverages video generators to jointly reconstruct 4D geometry and estimate dense motion from a monocular video. The key idea is a joint representation of dense 3D point maps and 3D scene flows in a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Ruijie Zhu , Jiahao Lu , Wenbo Hu , Xiaoguang Han , Jianfei Cai , Ying Shan , Chuanxia Zheng

Multi-object tracking (MOT) is a fundamental task in computer vision with critical applications in autonomous driving and robotics. Multimodal MOT that integrates visible light and thermal infrared information is particularly essential for…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Weiran Li , Yeqiang Liu , Yijie Wei , Mina Han , Qiannan Guo , Zhenbo Li

Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between…

Computer Vision and Pattern Recognition · Computer Science 2024-01-04 Yaozong Zheng , Bineng Zhong , Qihua Liang , Zhiyi Mo , Shengping Zhang , Xianxian Li