Related papers: EPIC Fields: Marrying 3D Geometry and Video Unders…
We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images. To do so, we learn a neural implicit field representing the density distribution of 3D edges which we refer to as Neural Edge…
We present Factor Fields, a novel framework for modeling and representing signals. Factor Fields decomposes a signal into a product of factors, each represented by a classical or neural field representation which operates on transformed…
Recent advances in implicit scene representation enable high-fidelity street view novel view synthesis. However, existing methods optimize a neural radiance field for each scene, relying heavily on dense training images and extensive…
Temporal correspondence - linking pixels or objects across frames - is a fundamental supervisory signal for the video models. For the panoptic understanding of dynamic scenes, we further extend this concept to every segment. Specifically,…
It is challenging for humans to enable visual knowledge discovery in data with more than 2-3 dimensions with a naked eye. This chapter explores the efficiency of discovering predictive machine learning models interactively using new…
In this paper, we explore an open research problem concerning the reconstruction of 3D scenes from images. Recent methods have adopt 3D Gaussian Splatting (3DGS) to produce 3D scenes due to its efficient training process. However, these…
Recent advances in feature learning have shown that self-supervised vision foundation models can capture semantic correspondences but often lack awareness of underlying 3D geometry. GECO addresses this gap by producing geometrically…
We present a novel approach for unsupervised learning of depth and ego-motion from monocular video. Unsupervised learning removes the need for separate supervisory signals (depth or ego-motion ground truth, or multi-view video). Prior work…
Neural Radiance Fields (NeRFs) can be dramatically accelerated by spatial grid representations. However, they do not explicitly reason about scale and so introduce aliasing artifacts when reconstructing scenes captured at different camera…
Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory. Previous methods rely on video generation models with external memory for consistency, or iterative 3D reconstruction and…
Data augmentation plays a critical role in improving model performance across various domains, but it becomes challenging with graph data due to their complex and irregular structure. To address this issue, we propose EPIC (Edit Path…
Reconstructing photo-realistic large-scale scenes from images, for example at city scale, is a long-standing problem in computer graphics. Neural rendering is an emerging technique that enables photo-realistic image synthesis from…
Robots benefit from high-fidelity reconstructions of their environment, which should be geometrically accurate and photorealistic to support downstream tasks. While this can be achieved by building distance fields from range sensors and…
The recent progress in implicit 3D representation, i.e., Neural Radiance Fields (NeRFs), has made accurate and photorealistic 3D reconstruction possible in a differentiable manner. This new representation can effectively convey the…
This technical report presents our solution, EgoAdapt (Egocentric Adaptation via Category, Calibration, and Consistency), to the CVPR 2026 HD-EPIC VQA challenge. HD-EPIC evaluates whether a vision-language model can reason over realistic…
With the spread of wearable devices and head mounted cameras, a wide range of application requiring precise user localization is now possible. In this paper we propose to treat the problem of obtaining the user position with respect to a…
We present a novel algorithm for estimating the broad 3D geometric structure of outdoor video scenes. Leveraging spatio-temporal video segmentation, we decompose a dynamic scene captured by a video into geometric classes, based on…
The recent advance of neural fields, such as neural radiance fields, has significantly pushed the boundary of scene representation learning. Aiming to boost the computation efficiency and rendering quality of 3D scenes, a popular line of…
Large-scale scene data is essential for training and testing in robot learning. Neural reconstruction methods have promised the capability of reconstructing large physically-grounded outdoor scenes from captured sensor data. However, these…
Recent advancements in 4D scene reconstruction using neural radiance fields (NeRF) have demonstrated the ability to represent dynamic scenes from multi-view videos. However, they fail to reconstruct the dynamic scenes and struggle to fit…