Related papers: Unified Semantic Transformer for 3D Scene Understa…
In recent years, the research community has shown a lot of interest to panoramic images that offer a 360-degree directional perspective. Multiple data modalities can be fed, and complimentary characteristics can be utilized for more robust…
Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a…
Volumetric depth map fusion based on truncated signed distance functions has become a standard method and is used in many 3D reconstruction pipelines. In this paper, we are generalizing this classic method in multiple ways: 1) Semantics:…
Perceiving a three-dimensional (3D) scene with multiple objects while moving indoors is essential for vision-based mobile cobots, especially for enhancing their manipulation tasks. In this work, we present an end-to-end pipeline with…
We propose a computational framework to jointly parse a single RGB image and reconstruct a holistic 3D configuration composed by a set of CAD models using a stochastic grammar model. Specifically, we introduce a Holistic Scene Grammar (HSG)…
Our goal is to develop stable, accurate, and robust semantic scene understanding methods for wide-area scene perception and understanding, especially in challenging outdoor environments. To achieve this, we are exploring and evaluating a…
To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene…
Scene Completion is the task of completing missing geometry from a partial scan of a scene. Most previous methods compute an implicit representation from range data using a Truncated Signed Distance Function (T-SDF) computed on a 3D grid as…
Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…
We study open-world 3D scene understanding, a family of tasks that require agents to reason about their 3D environment with an open-set vocabulary and out-of-domain visual inputs - a critical skill for robots to operate in the unstructured…
Reading irregular scene text of arbitrary shape in natural images is still a challenging problem, despite the progress made recently. Many existing approaches incorporate sophisticated network structures to handle various shapes, use extra…
In recent years, the paradigm of neural implicit representations has gained substantial attention in the field of Simultaneous Localization and Mapping (SLAM). However, a notable gap exists in the existing approaches when it comes to scene…
Time-resolved image sensors that capture light at pico-to-nanosecond timescales were once limited to niche applications but are now rapidly becoming mainstream in consumer devices. We propose low-cost and low-power imaging modalities that…
An effective pre-training framework with universal 3D representations is extremely desired in perceiving large-scale dynamic scenes. However, establishing such an ideal framework that is both task-generic and label-efficient poses a…
Recent conditional image synthesis approaches provide high-quality synthesized images. However, it is still challenging to accurately adjust image contents such as the positions and orientations of objects, and synthesized images often have…
In robotics, the effective integration of environmental data into actionable knowledge remains a significant challenge due to the variety and incompatibility of data formats commonly used in scene descriptions, such as MJCF, URDF, and SDF.…
LiDAR scene flow is the task of estimating per-point 3D motion between consecutive point clouds. Recent methods achieve centimeter-level accuracy on popular autonomous vehicle (AV) datasets, but are typically only trained and evaluated on a…
We present an unsupervised adaptation approach for visual scene understanding in unstructured traffic environments. Our method is designed for unstructured real-world scenarios with dense and heterogeneous traffic consisting of cars,…
Multi-task dense scene understanding is a thriving research domain that requires simultaneous perception and reasoning on a series of correlated tasks with pixel-wise prediction. Most existing works encounter a severe limitation of modeling…
We present an approach to infer a layer-structured 3D representation of a scene from a single input image. This allows us to infer not only the depth of the visible pixels, but also to capture the texture and depth for content in the scene…