Related papers: SSRFlow: Semantic-aware Fusion with Spatial Tempor…
A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based…
Over the past few years, deep convolutional neural network-based methods have made great progress in semantic segmentation of street scenes. Some recent methods align feature maps to alleviate the semantic gap between them and achieve high…
Understanding the motion states of the surrounding environment is critical for safe autonomous driving. These motion states can be accurately derived from scene flow, which captures the three-dimensional motion field of points. Existing…
We present ReFlow, a unified framework for monocular dynamic scene reconstruction that learns 3D motion in a novel self-correction manner from raw video. Existing methods often suffer from incomplete scene initialization for dynamic…
Scene flow estimation is a long-standing problem in computer vision, where the goal is to find the 3D motion of a scene from its consecutive observations. Recently, there have been efforts to compute the scene flow from 3D point clouds. A…
Rendering novel view images in dynamic scenes is a crucial yet challenging task. Current methods mainly utilize NeRF-based methods to represent the static scene and an additional time-variant MLP to model scene deformations, resulting in…
Autonomous robotic systems and self driving cars rely on accurate perception of their surroundings as the safety of the passengers and pedestrians is the top priority. Semantic segmentation is one the essential components of environmental…
Multi-modal 3D object understanding has gained significant attention, yet current approaches often assume complete data availability and rigid alignment across all modalities. We present CrossOver, a novel framework for cross-modal 3D scene…
Point scene understanding is a challenging task to process real-world scene point cloud, which aims at segmenting each object, estimating its pose, and reconstructing its mesh simultaneously. Recent state-of-the-art method first segments…
Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by…
Scene flow represents the motion information of each point in the 3D point clouds. It is a vital downstream method applied to many tasks, such as motion segmentation and object tracking. However, there are always occlusion points between…
Event cameras have shown promise in vision applications like optical flow estimation and stereo matching, with many specialized architectures leveraging the asynchronous and sparse nature of event data. However, existing works only focus…
3D scene graphs have recently emerged as a powerful high-level representation of 3D environments. A 3D scene graph describes the environment as a layered graph where nodes represent spatial concepts at multiple levels of abstraction and…
We present a novel approach for real-time joint reconstruction of 3D scene motion and geometry from binocular stereo videos. Our approach is based on a novel variational halfway-domain scene flow formulation, which allows us to obtain…
Feature fusion modules from encoder and self-attention module have been adopted in semantic segmentation. However, the computation of these modules is costly and has operational limitations in real-time environments. In addition,…
Existing offline feed-forward methods for joint scene understanding and reconstruction on long image streams often repeatedly perform global computation over an ever-growing set of past observations, causing runtime and GPU memory to…
The emergence of diffusion models has significantly advanced generative AI, improving the quality, realism, and creativity of image and video generation. Among them, Stable Diffusion (StableDiff) stands out as a key model for text-to-image…
We propose a novel scene flow estimation approach to capture and infer 3D motions from point clouds. Estimating 3D motions for point clouds is challenging, since a point cloud is unordered and its density is significantly non-uniform. Such…
In this paper we address the problem of human action recognition from video sequences. Inspired by the exemplary results obtained via automatic feature learning and deep learning approaches in computer vision, we focus our attention towards…
Online semantic 3D segmentation in company with real-time RGB-D reconstruction poses special challenges such as how to perform 3D convolution directly over the progressively fused 3D geometric data, and how to smartly fuse information from…