Related papers: LIFE: Lighting Invariant Flow Estimation
We propose a visual SLAM method by predicting and updating line flows that represent sequential 2D projections of 3D line segments. While feature-based SLAM methods have achieved excellent results, they still face problems in challenging…
Intrinsic Image Decomposition (IID) separates an image into albedo and shading components. It is a core step in many real-world applications, such as relighting and material editing. Existing IID models achieve good results, but often use a…
We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlike existing approaches which rely on brightness constancy and…
An end-to-end trainable ConvNet architecture, that learns to harness the power of shape representation for matching disparate image pairs, is proposed. Disparate image pairs are deemed those that exhibit strong affine variations in scale,…
When interacting with highly dynamic environments, scene flow allows autonomous systems to reason about the non-rigid motion of multiple independent objects. This is of particular interest in the field of autonomous driving, in which many…
We propose a novel data augmentation approach, DistractFlow, for training optical flow estimation models by introducing realistic distractions to the input frames. Based on a mixing ratio, we combine one of the frames in the pair with a…
Generative models have achieved remarkable progress with the emergence of flow matching (FM). It has demonstrated strong generative capabilities and attracted significant attention as a simulation-free flow-based framework capable of…
Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusions. Multi-frame supervision has the…
This article describes the implementation of the joint motion estimation and image reconstruction framework presented by Burger, Dirks and Sch\"onlieb and extends this framework to large-scale motion between consecutive image frames. The…
Continuous normalizing flows (CNFs) learn an ordinary differential equation to transform prior samples into data. Flow matching (FM) has recently emerged as a simulation-free approach for training CNFs by regressing a velocity model towards…
We propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, a SVBRDF, and 3D spatially-varying lighting. Because multi-view images provide a variety of information about the scene,…
Optical flow estimation is a fundamental task in computer vision. Recent direct-regression methods using deep neural networks achieve remarkable performance improvement. However, they do not explicitly capture long-term motion…
We introduce Prior-Informed Flow Matching (PIFM), a conditional flow model for graph reconstruction. Reconstructing graphs from partial observations remains a key challenge; classical embedding methods often lack global consistency, while…
Successful visual navigation depends upon capturing images that contain sufficient useful information. In this letter, we explore a data-driven approach to account for environmental lighting changes, improving the quality of images for use…
Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable.…
Object pose estimation is a fundamental problem in computer vision and plays a critical role in virtual reality and embodied intelligence, where agents must understand and interact with objects in 3D space. Recently, score based generative…
Long-term visual localization is an essential problem in robotics and computer vision, but remains challenging due to the environmental appearance changes caused by lighting and seasons. While many existing works have attempted to solve it…
Dense image correspondence is central to many applications, such as visual odometry, 3D reconstruction, object association, and re-identification. Historically, dense correspondence has been tackled separately for wide-baseline scenarios…
Although Structure-from-Motion (SfM) as a maturing technique has been widely used in many applications, state-of-the-art SfM algorithms are still not robust enough in certain situations. For example, images for inspection purposes are often…
Sparse optical flow is widely used in various computer vision tasks, however assuming brightness consistency limits its performance in High Dynamic Range (HDR) environments. In this work, a lightweight network is used to extract…