ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
Johns Hopkins University（约翰斯·霍普金斯大学）；Tsinghua University（清华大学）；Tongji University（同济大学）；University of Freiburg（弗赖堡大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Wufei Ma, Guanning Zeng, Guofeng Zhang, Qihao Liu, Letian Zhang, Adam Kortylewski, Yaoyao Liu, Alan Yuille
A vision model with general-purpose object-level 3D understanding should be capable of inferring both 2D (e.g., class name and bounding box) and 3D information (e.g., 3D location and 3D viewpoint) for arbitrary rigid objects in natural images. This is a challenging task, as it involves inferring 3D information from 2D signals and most importantly, generalizing to rigid objects from unseen categories. However, existing datasets with object-level 3D annotations are often limited by the number of categories or the quality of annotations. Models developed on these datasets become specialists for certain categories or domains, and fail to generalize. In this work, we present ImageNet3D, a large dataset for general-purpose object-level 3D understanding. ImageNet3D augments 200 categories from the ImageNet dataset with 2D bounding box, 3D pose, 3D location annotations, and image captions interleaved with 3D information. With the new annotations available in ImageNet3D, we could (i) analyze the object-level 3D awareness of visual foundation models, and (ii) study and develop general-purpose models that infer both 2D and 3D information for arbitrary rigid objects in natural images, and (iii) integrate unified 3D models with large language models for 3D-related reasoning.. We consider two new tasks, probing of object-level 3D awareness and open vocabulary pose estimation, besides standard classification and pose estimation. Experimental results on ImageNet3D demonstrate the potential of our dataset in building vision models with stronger general-purpose object-level 3D understanding.
Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images
Virginia Tech（弗吉尼亚理工大学）；The Ohio State University（俄亥俄州立大学）；Oak Ridge National Laboratory（橡树岭国家实验室）；University of California, Irvine（加州大学欧文分校）；Duke University（杜克大学）；Tulane University（杜兰大学）；Battelle（巴特尔纪念研究所）
Semantic understanding of 3D objects is crucial in many applications such as object manipulation. However, it is hard to give a universal definition of point-level semantics that everyone would agree on. We observe that people have a consensus on semantic correspondences between two areas from different objects, but are less certain about the exact semantic meaning of each area. Therefore, we argue that by providing human labeled correspondences between different objects from the same category instead of explicit semantic labels, one can recover rich semantic information of an object. In this …
South China University of Technology（华南理工大学）；I2R A-STAR（新加坡科技研究局资讯通信研究院）；Pazhou Laboratory（琶洲实验室）；Peng Cheng Laboratory（鹏城实验室）
The ability to understand the ways to interact with objects from visual cues, a.k.a. visual affordance, is essential to vision-guided robotic research. This involves categorizing, segmenting and reasoning of visual affordance. Relevant studies in 2D and 2.5D image domains have been made previously, however, a truly functional understanding of object affordance requires learning and prediction in the 3D physical domain, which is still absent in the community. In this work, we present a 3D AffordanceNet dataset, a benchmark of 23k shapes from 23 semantic object categories, annotated with 18 visu…
Recent approaches on visual scene understanding attempt to build a scene graph -- a computational representation of objects and their pairwise relationships. Such rich semantic representation is very appealing, yet difficult to obtain from a single image, especially when considering complex spatial arrangements in the scene. Differently, an image sequence conveys useful information using the multi-view geometric relations arising from camera motion. Indeed, in such cases, object relationships are naturally related to the 3D scene structure. To this end, this paper proposes a system that first …
Tsinghua University（清华大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Qi Zhi Institute（上海期智研究院）；Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Institute of Technology（北京理工大学）
Object-Uni: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS）；School of Vehicle and Mobility, Tsinghua University（清华大学车辆与 mobility学院）；Ant Group（蚂蚁集团）
We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset designed to help bridge the gap between real and virtual 3D worlds. ABO contains product catalog images, metadata, and artist-created 3D models with complex geometries and physically-based materials that correspond to real, household objects. We derive challenging benchmarks that exploit the unique properties of ABO and measure the current limits of the state-of-the-art on three open problems for real-world 3D object understanding: single-view 3D reconstruction, material estimation, and cross-domain multi-view object retriev…
University of Science and Technology of China（中国科学技术大学）
Affordance detection, which refers to perceiving objects with potential action possibilities in images, is a challenging task since the possible affordance depends on the person's purpose in real-world application scenarios. The existing works mainly extract the inherent human-object dependencies from image/video to accommodate affordance properties that change dynamically. In this paper, we explore to perceive affordance from a vision-language perspective and consider the challenging phrase-based affordance detection problem,i.e., given a set of phrases describing the action purposes, all the…
Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?
School of Artificial Intelligence and Robotics, Hunan University（湖南大学人工智能与机器人学院）；Intelligent Game and Decision Lab (IGDL)（智能游戏与决策实验室）；Yuelushan Center for Industrial Innovation（岳麓山工业创新中心）
Samsung AI Center Moscow（三星人工智能中心莫斯科）；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）
In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem. To address this problem, we propose ImVoxelNet, a novel fully convolutional method of 3D object detection based on monocular or multi-view RGB images. The number of monocular images in each multi-view input can variate during training and inference; actually, this number might be unique for each multi-view input. ImVoxelNet successfully handles both indoor and outdoor scenes, which makes it general-purpose. Specifically, it achieves state-of-the-art results in car detection o…
VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding
ETH Zurich（苏黎世联邦理工学院）；University of Central Florida（中佛罗里达大学）；Khalifa University（哈利法大学）；Mohamed Bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）
Georgia Institute of Technology（佐治亚理工学院）；Georgia Tech Research Institute（佐治亚理工研究院）
Perception is an essential part of robotic manipulation in a semi-structured environment. Traditional approaches produce a narrow task-specific prediction (e.g., object's 6D pose), that cannot be adapted to other tasks and is ill-suited for deformable objects. In this paper, we propose using canonical mapping as a near-universal and flexible object descriptor. We demonstrate that common object representations can be derived from a single pre-trained canonical mapping model, which in turn can be generated with minimal manual effort using an automated data generation and training pipeline. We pe…
University of Washington（华盛顿大学）；Allen Institute for AI (AI2)（艾伦人工智能研究所（AI2））
We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise dilated separable convolutions to learn representations from a large effective receptive field with fewer FLOPs and parameters. The performance of our network is evaluated on four different tasks: (1) object classification, (2) semantic segmentation, (3) object detection, and (4) language modeling. Experiments on these tasks, including image classification on the ImageNet and language modeling on the …
Microsoft（微软）；State University of New York at Buffalo（纽约州立大学布法罗分校）
This paper presents a Generative RegIon-to-Text transformer, GRiT, for object understanding. The spirit of GRiT is to formulate object understanding as <region, text> pairs, where region locates objects and text describes objects. For example, the text in object detection denotes class names while that in dense captioning refers to descriptive sentences. Specifically, GRiT consists of a visual encoder to extract image features, a foreground object extractor to localize objects, and a text decoder to generate open-set object descriptions. With the same model architecture, GRiT can understand ob…
MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding
Tsinghua University（清华大学）；The University of Sydney（悉尼大学）；University of Science and Technology of China（中国科学技术大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Intime Department Store（Intime百货）；Deepeleph；HKUST（香港科技大学）
The visual observation and tracking of cells and other micrometer-sized objects has many different biomedical applications. The automation of those tasks based on computer methods helps in the evaluation of such measurements. In this work, we present a general purpose algorithm that excels at evaluating deterministic behavior of micrometer-sized objects. Our concrete application is the tracking of fast moving objects over large distances along deterministic trajectories in a microscopic video. Thereby, we are able to determine characteristic properties of the objects. For this purpose, we use …
Training effective embodied AI agents often involves manual reward engineering, expert imitation, specialized components such as maps, or leveraging additional sensors for depth and localization. Another approach is to use neural architectures alongside self-supervised objectives which encourage better representation learning. In practice, there are few guarantees that these self-supervised objectives encode task-relevant information. We propose the Scene Graph Contrastive (SGC) loss, which uses scene graphs as general-purpose, training-only, supervisory signals. The SGC loss does away with ex…
University of Science and Technology of China（中国科学技术大学）；JD Explore Academy, JD.com（京东集团京东探索研究院）；The University of Sydney（悉尼大学）
Affordance detection refers to identifying the potential action possibilities of objects in an image, which is an important ability for robot perception and manipulation. To empower robots with this ability in unseen scenarios, we consider the challenging one-shot affordance detection problem in this paper, i.e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected. To this end, we devise a One-Shot Affordance Detection (OS-AD) network that firstly estimates the purpose and then transfers it to help detect the common afford…
Institute of Industrial Science, The University of Tokyo（东京大学生产技术研究所）；Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
This paper proposes a novel method for understanding daily hand-object manipulation by developing computer vision-based techniques. Specifically, we focus on recognizing hand grasp types, object attributes and manipulation actions within an unified framework by exploring their contextual relationships. Our hypothesis is that it is necessary to jointly model hands, objects and actions in order to accurately recognize multiple tasks that are correlated to each other in hand-object manipulation. In the proposed model, we explore various semantic relationships between actions, grasp types and obje…
We try to address the problem of document layout understanding using a simple algorithm which generalizes across multiple domains while training on just few examples per domain. We approach this problem via supervised object detection method and propose a methodology to overcome the requirement of large datasets. We use the concept of transfer learning by pre-training our object detector on a simple artificial (source) dataset and fine-tuning it on a tiny domain specific (target) dataset. We show that this methodology works for multiple domains with training samples as less as 10 documents. We…
University of Science and Technology of China（中国科学技术大学）；The University of Sydney（悉尼大学）；JD Explore Academy（京东探索研究院）
Affordance detection refers to identifying the potential action possibilities of objects in an image, which is a crucial ability for robot perception and manipulation. To empower robots with this ability in unseen scenarios, we first study the challenging one-shot affordance detection problem in this paper, i.e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected. To this end, we devise a One-Shot Affordance Detection Network (OSAD-Net) that firstly estimates the human action purpose and then transfers it to help detect t…
Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）；Peking University（北京大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Beijing Institute of Technology（北京理工大学）
Current computer vision models, unlike the human visual system, cannot yet achieve general-purpose visual understanding. Existing efforts to create a general vision model are limited in the scope of assessed tasks and offer no overarching framework to perform them holistically. We present a new comprehensive benchmark, General-purpose Visual Understanding Evaluation (G-VUE), covering the full spectrum of visual cognitive abilities with four functional domains $\unicode{x2014}$ Perceive, Ground, Reason, and Act. The four domains are embodied in 11 carefully curated tasks, from 3D reconstruction…
Referring expressions usually describe an object using properties of the object and relationships of the object with other objects. We propose a technique that integrates context between objects to understand referring expressions. Our approach uses an LSTM to learn the probability of a referring expression, with input features from a region and a context region. The context regions are discovered using multiple-instance learning (MIL) since annotations for context objects are generally not available for training. We utilize max-margin based MIL objective functions for training the LSTM. Exper…
Technical University of Munich（慕尼黑工业大学）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所）；New York University（纽约大学）
Recent advances in 3D semantic scene understanding have shown impressive progress in 3D instance segmentation, enabling object-level reasoning about 3D scenes; however, a finer-grained understanding is required to enable interactions with objects and their functional understanding. Thus, we propose the task of part-based scene understanding of real-world 3D environments: from an RGB-D scan of a scene, we detect objects, and for each object predict its decomposition into geometric part masks, which composed together form the complete geometry of the observed object. We leverage an intermediary …
Georgia Institute of Technology（佐治亚理工学院）；NEC Laboratories America（美国NEC实验室）；Georgia Tech Research Institute（佐治亚理工研究院）
Human actions often involve complex interactions across several inter-related objects in the scene. However, existing approaches to fine-grained video understanding or visual relationship detection often rely on single object representation or pairwise object relationships. Furthermore, learning interactions across multiple objects in hundreds of frames for video is computationally infeasible and performance may suffer since a large combinatorial space has to be modeled. In this paper, we propose to efficiently learn higher-order interactions between arbitrary subgroups of objects for fine-gra…
Learning how humans manipulate objects requires machines to acquire knowledge from two perspectives: one for understanding object affordances and the other for learning human's interactions based on the affordances. Even though these two knowledge bases are crucial, we find that current databases lack a comprehensive awareness of them. In this work, we propose a multi-modal and rich-annotated knowledge repository, OakInk, for visual and cognitive understanding of hand-object interactions. We start to collect 1,800 common household objects and annotate their affordances to construct the first k…
Video understanding is one of the most challenging topics in computer vision. In this paper, a four-stage video understanding pipeline is presented to simultaneously recognize all atomic actions and the single on-going activity in a video. This pipeline uses objects and motions from the video and a graph-based knowledge representation network as prior reference. Two deep networks are trained to identify objects and motions in each video sequence associated with an action. Low Level image features are then used to identify objects of interest in that video sequence. Confidence scores are assign…
From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学）；Peking University（北京大学）；Tencent Youtu Lab（腾讯优图实验室）
Bournemouth University（伯恩茅斯大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Xiamen University（厦门大学）
Semantic reconstruction of indoor scenes refers to both scene understanding and object reconstruction. Existing works either address one part of this problem or focus on independent objects. In this paper, we bridge the gap between understanding and reconstruction, and propose an end-to-end solution to jointly reconstruct room layout, object bounding boxes and meshes from a single image. Instead of separately resolving scene understanding and object reconstruction, our method builds upon a holistic scene context and proposes a coarse-to-fine hierarchy with three components: 1. room layout with…
University of Electronic Science and Technology of China（电子科技大学）；Google（谷歌）；ETH Zürich（苏黎世联邦理工学院）
We present a new pipeline for holistic 3D scene understanding from a single image, which could predict object shapes, object poses, and scene layout. As it is a highly ill-posed problem, existing methods usually suffer from inaccurate estimation of both shapes and layout especially for the cluttered scene due to the heavy occlusion between objects. We propose to utilize the latest deep implicit representation to solve this challenge. We not only propose an image-based local structured implicit network to improve the object shape estimation, but also refine the 3D object pose and scene layout v…
ETH Zurich（苏黎世联邦理工学院）；Imperial College London（帝国理工学院）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Swiss Federal Institute of Technology (ETH), Zurich（苏黎世联邦理工学院）
Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are robust and allow for reliable object detection, they discard much of the information about objects' 3D shape and pose, and thus do not lend themselves well to higher-level reasoning. Here, we propose to base scene understanding on a high-resolution object representation. An object class - in our case cars - is modeled as a deformable 3D wireframe, which enables fine-grained modeling at the level of individual vertices a…
As a core problem in computer vision, the performance of object detection has improved drastically in the past few years. Despite their impressive performance, object detectors suffer from a lack of interpretability. Visualization techniques have been developed and widely applied to introspect the decisions made by other kinds of deep learning models; however, visualizing object detectors has been underexplored. In this paper, we propose using inversion as a primary tool to understand modern object detectors and develop an optimization-based approach to layout inversion, allowing us to generat…
This paper presents a review of human activity recognition and behaviour understanding in video sequence. The key objective of this paper is to provide a general review on the overall process of a surveillance system used in the current trend. Visual surveillance system is directed on automatic identification of events of interest, especially on tracking and classification of moving objects. The processing step of the video surveillance system includes the following stages: Surrounding model, object representation, object tracking, activity recognition and behaviour understanding. It describes…
Allen Institute for Artificial Intelligence (AI2)（艾伦人工智能研究所（AI2））；University of Washington（华盛顿大学）
In this paper, we study the challenging problem of predicting the dynamics of objects in static images. Given a query object in an image, our goal is to provide a physical understanding of the object in terms of the forces acting upon it and its long term motion as response to those forces. Direct and explicit estimation of the forces and the motion of objects from a single image is extremely challenging. We define intermediate physical abstractions called Newtonian scenarios and introduce Newtonian Neural Network ($N^3$) that learns to map a single image to a state in a Newtonian scenario. Ou…
University of California, Los Angeles (UCLA)（加州大学洛杉矶分校）；International Center for AI and Robot Autonomy (CARA)（国际人工智能与机器人自主中心）
We propose a new 3D holistic++ scene understanding problem, which jointly tackles two tasks from a single-view image: (i) holistic scene parsing and reconstruction---3D estimations of object bounding boxes, camera pose, and room layout, and (ii) 3D human pose estimation. The intuition behind is to leverage the coupled nature of these two tasks to improve the granularity and performance of scene understanding. We propose to exploit two critical and essential connections between these two tasks: (i) human-object interaction (HOI) to model the fine-grained relations between agents and objects in …
What would be the effect of locally poking a static scene? We present an approach that learns naturally-looking global articulations caused by a local manipulation at a pixel level. Training requires only videos of moving objects but no information of the underlying manipulation of the physical scene. Our generative model learns to infer natural object dynamics as a response to user interaction and learns about the interrelations between different object body regions. Given a static image of an object and a local poking of a pixel, the approach then predicts how the object would deform over ti…
CoralscapesV2: Panoptic and Fine-Grained Visual Scene Understanding in Coral Reefs
MIT（麻省理工学院）；EPFL（洛桑联邦理工学院）；University of Djibouti（吉布提大学）；Ministry of Environment and Sustainable Development of Djibouti（吉布提环境与可持续发展部）；Centre d’Études et de Recherche de Djibouti（吉布提研究与研究中心）；Red Sea University of Port Sudan（苏丹港红海大学）；Aqaba Marine Reserve, Jordan（约旦亚喀巴海洋保护区）；United Nations Development Programme Jordan（联合国开发计划署约旦办事处）；Mai Nefhi College of Science, Eritrea（厄立特里亚马伊内菲理学院）；Ministry of Marine Resources, Massawa, Eritrea（厄立特里亚马萨瓦海洋资源部）
