Related papers: Vid2CAD: CAD Model Alignment using Multi-View Cons…

Video object segmentation methods like SAM2 achieve strong performance through memory-based architectures but struggle under large viewpoint changes due to reliance on appearance features. Traditional 3D instance segmentation methods…

Efficiently reconstructing 3D scenes from monocular video remains a core challenge in computer vision, vital for applications in virtual reality, robotics, and scene understanding. Recently, frame-by-frame progressive reconstruction without…

Deploying visual reinforcement learning (RL) policies in real-world manipulation is often hindered by camera viewpoint changes. A policy trained from a fixed front-facing camera may fail when the camera is shifted -- an unavoidable…

Recently, the advancement of self-supervised learning techniques, like masked autoencoders (MAE), has greatly influenced visual representation learning for images and videos. Nevertheless, it is worth noting that the predominant approaches…

Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their…

We present Image2GS, a novel approach that addresses the challenging problem of reconstructing photorealistic 3D scenes from a single image by focusing specifically on the image-to-3D lifting component of the reconstruction process. By…

Scene graph alignment establishes object correspondences between two 3D scene graphs constructed from partially overlapping observations. This enables efficient scene understanding and object-level relocalization when a robot revisits a…

A key question in the problem of 3D reconstruction is how to train a machine or a robot to model 3D objects. Many tasks like navigation in real-time systems such as autonomous vehicles directly depend on this problem. These systems usually…

Multi-camera surveillance has been an active research topic for understanding and modeling scenes. Compared to a single camera, multi-cameras provide larger field-of-view and more object cues, and the related applications are multi-view…

Existing inverse physics methods recover physical parameters from multi-view videos, where geometric constraints across views resolve scale and 3D structure. In monocular settings, however, such constraints are absent, leading to severe…

Spatial intelligence is a critical frontier for Multimodal Large Language Models (MLLMs), empowering them to comprehend the physical world. Drawing inspiration from human perception mechanisms, prior studies attempt to construct a spatial…

The prospect of assistive robots aiding in object organization has always been compelling. In an image-goal setting, the robot rearranges the current scene to match the single image captured from the goal scene. The key to an image-goal…

We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a setting that arises naturally when multiple observers capture a shared event. Prior approaches…

A long-standing challenge in scene analysis is the recovery of scene arrangements under moderate to heavy occlusion, directly from monocular video. While the problem remains a subject of active research, concurrent advances have been made…

The field of collaborative robotics and human-robot interaction often focuses on the prediction of human behaviour, while assuming the information about the robot setup and configuration being known. This is often the case with fixed…

Computer vision is largely based on 2D techniques, with 3D vision still relegated to a relatively narrow subset of applications. However, by building on recent advances in 3D models such as neural radiance fields, some authors have shown…

Multi-view 3D reconstruction remains a core challenge in computer vision. Recent methods, such as DUST3R and its successors, directly regress pointmaps from image pairs without relying on known scene geometry or camera parameters. However,…

Image-based localization, or camera relocalization, is a fundamental problem in computer vision and robotics, and it refers to estimating camera pose from an image. Recent state-of-the-art approaches use learning based methods, such as…

We propose a method to detect and reconstruct multiple 3D objects from a single RGB image. The key idea is to optimize for detection, alignment and shape jointly over all objects in the RGB image, while focusing on realistic and physically…

We propose a weakly-supervised multi-view learning approach to learn category-specific surface mapping without dense annotations. We learn the underlying surface geometry of common categories, such as human faces, cars, and airplanes, given…