Related papers: Continuous 3D Perception Model with Persistent Sta…
Generative models have proven effective at modeling 3D shapes and their statistical variations. In this paper we investigate their application to point clouds, a 3D shape representation widely used in computer vision for which, however,…
Image stitching aim to align two images taken from different viewpoints into one seamless, wider image. However, when the 3D scene contains depth variations and the camera baseline is significant, noticeable parallax occurs-meaning the…
High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm often suffers from…
Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly…
World building with 3D scene representations is increasingly important for content creation, simulation, and interactive experiences, yet real workflows are inherently iterative: creators must repeatedly extend an existing scene under user…
We present AMB3R, a multi-view feed-forward model for dense 3D reconstruction on a metric-scale that addresses diverse 3D vision tasks. The key idea is to leverage a sparse, yet compact, volumetric scene representation as our backend,…
Knowledge of 3D properties of objects is a necessity in order to build effective computer vision systems. However, lack of large scale 3D datasets can be a major constraint for data-driven approaches in learning such properties. We consider…
Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem due to its computational complexity and inherent visual ambiguities. Most dense incremental reconstruction systems…
Novel view synthesis with neural models has advanced rapidly in recent years, yet adapting these models to scene changes remains an open problem. Existing methods are either labor-intensive, requiring extensive model retraining, or fail to…
We present a recurrent network for the 3D reconstruction of neurons that sequentially generates binary masks for every object in an image with spatio-temporal consistency. Our network models consistency in two parts: (i) local, which allows…
We are witnessing an explosion of neural implicit representations in computer vision and graphics. Their applicability has recently expanded beyond tasks such as shape generation and image-based rendering to the fundamental problem of…
Thin structures, such as wire-frame sculptures, fences, cables, power lines, and tree branches, are common in the real world. It is extremely challenging to acquire their 3D digital models using traditional image-based or depth-based…
We present a latent diffusion model for fast feed-forward 3D scene generation. Given one or more images, our model Bolt3D directly samples a 3D scene representation in less than seven seconds on a single GPU. We achieve this by leveraging…
We explore total scene capture -- recording, modeling, and rerendering a scene under varying appearance such as season and time of day. Starting from internet photos of a tourist landmark, we apply traditional 3D reconstruction to register…
3D scene understanding for robotic applications exhibits a unique set of requirements including real-time inference, object-centric latent representation learning, accurate 6D pose estimation and 3D reconstruction of objects. Current…
The field of 3D object detection from point clouds is rapidly advancing in computer vision, aiming to accurately and efficiently detect and localize objects in three-dimensional space. Current 3D detectors commonly fall short in terms of…
We present an efficient and automatic approach for accurate reconstruction of instances of big 3D objects from multiple, unorganized and unstructured point clouds, in presence of dynamic clutter and occlusions. In contrast to conventional…
We present a deep reinforcement learning method of progressive view inpainting for colored semantic point cloud scene completion under volume guidance, achieving high-quality scene reconstruction from only a single RGB-D image with severe…
The latest developments in 3D capturing, processing, and rendering provide means to unlock novel 3D application pathways. The main elements of an integrated platform, which target tele-immersion and future 3D applications, are described in…
Transformer-based 3D reconstruction has emerged as a powerful paradigm for recovering geometry and appearance from multi-view observations, offering strong performance across challenging visual conditions. As these models scale to larger…