Related papers: L4P: Towards Unified Low-Level 4D Vision Perceptio…
Understanding the real world through point cloud video is a crucial aspect of robotics and autonomous driving systems. However, prevailing methods for 4D point cloud recognition have limitations due to sensor resolution, which leads to a…
Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise. In this paper, we present an innovative video decomposition strategy that incorporates view-independent and…
4D radar measurements offer an affordable and weather-robust solution for 3D perception. However, the inherent sparsity and noise of radar point clouds present significant challenges for accurate 3D object detection, underscoring the need…
We present a method that decomposes, or "unwraps", an input video into a set of layered 2D atlases, each providing a unified representation of the appearance of an object (or background) over the video. For each pixel in the video, our…
The challenging task of 3D planar reconstruction from images involves several sub-tasks including frame-wise plane detection, segmentation, parameter regression and possibly depth prediction, along with cross-frame plane correspondence and…
We introduce a multi-scale framework for low-level vision, where the goal is estimating physical scene values from image data---such as depth from stereo image pairs. The framework uses a dense, overlapping set of image regions at multiple…
Efficiently transferring Learned Image Compression (LIC) model from human perception to machine perception is an emerging challenge in vision-centric representation learning. Existing approaches typically adapt LIC to downstream tasks in a…
General perception systems such as Perceivers can process arbitrary modalities in any combination and are able to handle up to a few hundred thousand inputs. They achieve this generality by using exclusively global attention operations.…
Generative models have shown a giant leap in synthesizing photo-realistic images with minimal expertise, sparking concerns about the authenticity of online information. This study aims to develop a universal AI-generated image detector…
Video understanding aims to enable models to perceive, reason about, and interact with the dynamic visual world. In contrast to image understanding, video understanding inherently requires modeling temporal dynamics and evolving visual…
Image pyramids are widely adopted in top-performing methods to obtain multi-scale features for precise visual perception and understanding. However, current image pyramids use the same large-scale model to process multiple resolutions of…
Cooperative perception allows connected vehicles and roadside infrastructure to share sensor observations, creating a fused scene representation beyond the capability of any single platform. However, most cooperative 3D object detectors use…
Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video…
Low-overhead visual place recognition (VPR) is a highly active research topic. Mobile robotics applications often operate under low-end hardware, and even more hardware capable systems can still benefit from freeing up onboard system…
Dynamic spatial reasoning from monocular video is essential for bridging visual intelligence and the physical world, yet remains challenging for vision-language models (VLMs). Prior approaches either verbalize spatial-temporal reasoning…
Recognition and reasoning are two pillars of visual understanding. However, these tasks have an imbalance in focus; whereas recent advances in neural networks have shown strong empirical performance in visual recognition, there has been…
Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras and strong prior constraints. This paper introduces a…
We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image. Our approach unifies the generative priors of video diffusion models with geometry and motion constraints learned from…
Current robotic planning methods often rely on predicting multi-frame images with full pixel details. While this fine-grained approach can serve as a generic world model, it introduces two significant challenges for downstream policy…
Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes $T$ times longer sequence than the latter under the current attention of quadratic complexity $(T^2N^2)$. The existing…