Related papers: TrajVG: 3D Trajectory-Coupled Visual Geometry Lear…

The intuitive nature of drag-based interaction has led to its growing adoption for controlling object trajectories in image-to-video synthesis. Still, existing methods that perform dragging in the 2D space usually face ambiguity when…

Recognizing instruments' interactions with tissues is essential for building context-aware AI assistants in robotic surgery. Vision-language models (VLMs) have opened a new avenue for surgical perception and achieved better generalization…

We hypothesize that an agent that can look around in static scenes can learn rich visual representations applicable to 3D object tracking in complex dynamic scenes. We are motivated in this pursuit by the fact that the physical world itself…

Learning deformable 3D objects from 2D images is often an ill-posed problem. Existing methods rely on explicit supervision to establish multi-view correspondences, such as template shape models and keypoint annotations, which restricts…

We propose an approach to predict the 3D shape and pose for the objects present in a scene. Existing learning based methods that pursue this goal make independent predictions per object, and do not leverage the relationships amongst them.…

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…

We propose a new method to estimate the 6-dof trajectory of a flying object such as a quadrotor UAV within a 3D airspace monitored using multiple fixed ground cameras. It is based on a new structure from motion formulation for the 3D…

This study seeks to automate camera movement control for filming existing subjects into attractive videos, contrasting with the creation of non-existent content by directly generating the pixels. We select drone videos as our test case due…

In this paper, we propose PETRv2, a unified framework for 3D perception from multi-view images. Based on PETR, PETRv2 explores the effectiveness of temporal modeling, which utilizes the temporal information of previous frames to boost 3D…

Recent feed-forward networks have achieved remarkable progress in sparse-view 3D reconstruction by predicting dense point maps directly from RGB images. However, they often suffer from geometric inconsistencies and limited fine-grained…

In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks. However, when extended to…

In monocular videos that capture dynamic scenes, estimating the 3D geometry of video contents has been a fundamental challenge in computer vision. Specifically, the task is significantly challenged by the object motion, where existing…

Predictive coding theories suggest that the brain learns by predicting observations at various levels of abstraction. One of the most basic prediction tasks is view prediction: how would a given scene look from an alternative viewpoint?…

With the prevalence of LiDAR sensors in autonomous driving, 3D object tracking has received increasing attention. In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in consecutive frames…

The emerging trend in computer vision emphasizes developing universal models capable of simultaneously addressing multiple diverse tasks. Such universality typically requires joint training across multi-domain datasets to ensure effective…

Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically…

Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Supervised Fine-Tuning using synthetic datasets. At present, there is an extreme…

Given unstructured videos of deformable objects, we automatically recover spatiotemporal correspondences to map one object to another (such as animals in the wild). While traditional methods based on appearance fail in such challenging…

This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to…

Despite receiving significant attention from the research community, the task of segmenting and tracking objects in monocular videos still has much room for improvement. Existing works have simultaneously justified the efficacy of dilated…