Related papers: Visual Acuity Consistent Foveated Rendering toward…
In this paper, we propose a new image-based visual place recognition (VPR) framework by exploiting the structural cues in bird's-eye view (BEV) from a single monocular camera. The motivation arises from two key observations about place…
Infrared and visible video fusion combines the object saliency from infrared images with the texture details from visible images to produce semantically rich fusion results. However, most existing methods are designed for static image…
Visual Odometry (VO) is essential to downstream mobile robotics and augmented/virtual reality tasks. Despite recent advances, existing VO methods still rely on heuristic design choices that require several weeks of hyperparameter tuning by…
In the present paper, we discuss the design of a projection system with curved display and its enhancement by variably adjusting the curvature. We demonstrate that the focal surface curvature varies significantly with a change of the object…
The neural rendering of humans is a topic of great research significance. However, previous works mostly focus on achieving photorealistic details, neglecting the exploration of human parsing. Additionally, classical semantic work are all…
HEVC contains an option to enable custom quantization matrices, which are designed based on the Human Visual System and a 2D Contrast Sensitivity Function. Visual Display Units, capable of displaying video data at High Definition and Ultra…
The real world is dynamic, yet most image fusion methods process static frames independently, ignoring temporal correlations in videos and leading to flickering and temporal inconsistency. To address this, we propose Unified Video Fusion…
We propose a differentiable rendering algorithm for efficient novel view synthesis. By departing from volume-based representations in favor of a learned point representation, we improve on existing methods more than an order of magnitude in…
This paper introduces PanoRadar, a novel RF imaging system that brings RF resolution close to that of LiDAR, while providing resilience against conditions challenging for optical signals. Our LiDAR-comparable 3D imaging results enable, for…
We propose a simple yet effective neural network-based framework for global illumination rendering. Recently, rendering techniques that learn neural radiance caches by minimizing the difference (i.e., residual) between the left and right…
We introduce VistaFlow, a scalable three-dimensional imaging technique capable of reconstructing fully interactive 3D volumetric images from a set of 2D photographs. Our model synthesizes novel viewpoints through a differentiable rendering…
We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on adaptive sparse voxels without neural networks or 3D Gaussians. There are two key contributions coupled with the proposed system. The…
In the learning based video compression approaches, it is an essential issue to compress pixel-level optical flow maps by developing new motion vector (MV) encoders. In this work, we propose a new framework called Resolution-adaptive Flow…
This paper investigates whether a custom varifocal display can improve 3D pointing performance in augmented reality (AR), where the vergence-accommodation conflict (VAC) is known to impair interaction. Varifocal displays have been…
Neural representations for video (NeRV) have gained considerable attention for their strong performance across various video tasks. However, existing NeRV methods often struggle to capture fine spatial details, resulting in vague…
The goal of this work is to characterize the representational impact that foveation operations have for machine vision systems, inspired by the foveated human visual system, which has higher acuity at the center of gaze and texture-like…
Multimodal question answering (QA) often requires identifying which video, audio, or sensor tokens are relevant to the question. Yet modality disagreements are common: off-camera speech, background noise, or motion outside the field of view…
Research and medicine rely on non-invasive optical techniques to image living tissue with high resolution in space and time. But so far a single data acquisition could not provide entirely diffraction-limited tomographic volumes of rapidly…
Differentiable volumetric rendering-based methods made significant progress in novel view synthesis. On one hand, innovative methods have replaced the Neural Radiance Fields (NeRF) network with locally parameterized structures, enabling…
Integrating LiDAR and camera information in the bird's eye view (BEV) representation has demonstrated its effectiveness in 3D object detection. However, because of the fundamental disparity in geometric accuracy between these sensors,…