The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e.g. point clouds) are notoriously hard. For example, the number of scenes (e.g. indoor rooms) that can be accessed and scanned might be limited; even given sufficient data, acquiring 3D labels (e.g. instance masks) requires intensive human labor. In this paper, we explore data-efficient learning for 3D point cloud. As a first step towards this direction, we propose Contrastive Scene Contexts, a 3D pre-training method that makes use of both point-level correspondences and spatial contexts in a scene. Our method achieves state-of-the-art results on a suite of benchmarks where training data or labels are scarce. Our study reveals that exhaustive labelling of 3D point clouds might be unnecessary; and remarkably, on ScanNet, even using 0.1% of point labels, we still achieve 89% (instance segmentation) and 96% (semantic segmentation) of the baseline performance that uses full annotations.
We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness, and thus propose to imbue learned 3D representations with such dynamic understanding, that can then be effectively transferred to improved performance in downstream 3D semantic scene understanding tasks. We propose a new data augmentation scheme leveraging synthetic 3D shapes moving in static 3D environments, and employ contrastive learning under 3D-4D constr…
In this work, we leverage estimated depth to boost self-supervised contrastive learning for segmentation of urban scenes, where unlabeled videos are readily available for training self-supervised depth estimation. We argue that the semantics of a coherent group of pixels in 3D space is self-contained and invariant to the contexts in which they appear. We group coherent, semantically related pixels into coherent depth regions given their estimated depth and use copy-paste to synthetically vary their contexts. In this way, cross-context correspondences are built in contrastive learning and a con…
This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos, agnostic to object and scene semantic content, and evaluates the resulting scene representations in the downstream tasks of visual correspondence, object tracking, and object detection. The model infers a latent3D representation of the scene in the form of 3D feature points, where each continuous world 3D point is mapped to its corresponding feature vector. The model is trained for contrastive view prediction by rendering 3D feature clouds in queried viewpoints and matc…
As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale unsupervised learning in 3D has yet to emerge due to two stumbling blocks: the inefficiency of matching RGB-D frames as contrastive views and the annoying mode collapse phenomenon mentioned in previous works. Turning the two stumbling blocks into empirical stepping stones, we first propose an efficient and effective contrastive learning framework, which generates…
Model2Scene: Learning 3D Scene Representation via Contrastive Language-CAD Models Pre-training
The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）；Inceptio（嬴彻科技）；ShanghaiTech University（上海科技大学）；The University of Sydney（悉尼大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Texas A&M University（德克萨斯农工大学）
UC Berkeley（加州大学伯克利分校）；Facebook AI Research（脸书人工智能研究院）
In this paper we explore two ways of using context for object detection. The first model focusses on people and the objects they commonly interact with, such as fashion and sports accessories. The second model considers more general object detection and uses the spatial relationships between objects and between objects and scenes. Our models are able to capture precise spatial relationships between the context and the object of interest, and make effective use of the appearance of the contextual region. On the newly released COCO dataset, our models provide relative improvements of up to 5% ov…
Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；School of Computer Science and Technology, Hainan University（海南大学计算机科学与技术学院）；School of Electronic Information, Wuhan University（武汉大学电子信息学院）；State Key Lab. of LIESMARS, Wuhan University（武汉大学LIESMARS国家重点实验室）；Institute for Math & AI, Wuhan University（武汉大学数学与人工智能研究院）
Multi-scale Contrastive Adaptor Learning for Segmenting Anything in Underperformed Scenes
School of Automation and Electrical Engineering, University of Science and Technology Beijing（北京科技大学自动化与电气工程学院）；Alibaba DAMO Academy（阿里巴巴达摩院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）
Peking University（北京大学）；China North Vehicle Research Institute（中国北方车辆研究所）
Off-road semantic segmentation with fine-grained labels is necessary for autonomous vehicles to understand driving scenes, as the coarse-grained road detection can not satisfy off-road vehicles with various mechanical properties. Fine-grained semantic segmentation in off-road scenes usually has no unified category definition due to ambiguous nature environments, and the cost of pixel-wise labeling is extremely high. Furthermore, semantic properties of off-road scenes can be very changeable due to various precipitations, temperature, defoliation, etc. To address these challenges, this research …
Predictive coding theories suggest that the brain learns by predicting observations at various levels of abstraction. One of the most basic prediction tasks is view prediction: how would a given scene look from an alternative viewpoint? Humans excel at this task. Our ability to imagine and fill in missing information is tightly coupled with perception: we feel as if we see the world in 3 dimensions, while in fact, information from only the front surface of the world hits our retinas. This paper explores the role of view prediction in the development of 3D visual recognition. We propose neural …
Peking University（北京大学）；China North Vehicle Research Institute（中国北方车辆研究所）
Road detection or traversability analysis has been a key technique for a mobile robot to traverse complex off-road scenes. The problem has been mainly formulated in early works as a binary classification one, e.g. associating pixels with road or non-road labels. Whereas understanding scenes with fine-grained labels are needed for off-road robots, as scenes are very diverse, and the various mechanical performance of off-road robots may lead to different definitions of safe regions to traverse. How to define and annotate fine-grained labels to achieve meaningful scene understanding for a robot t…
University of Maryland, College Park（马里兰大学帕克分校）；Google Research（谷歌研究院）；Meta
Although self-/un-supervised methods have led to rapid progress in visual representation learning, these methods generally treat objects and scenes using the same lens. In this paper, we focus on learning representations for objects and scenes that preserve the structure among them. Motivated by the observation that visually similar objects are close in the representation space, we argue that the scenes and objects should instead follow a hierarchical structure based on their compositionality. To exploit such a structure, we propose a contrastive learning framework where a Euclidean loss is us…
National University of Sciences and Technology (NUST)（国立科技大学）；Technical University of Munich (TUM)（慕尼黑工业大学）；German Aerospace Center (DLR)（德国航空航天中心）
Semantic segmentation of raw 3D point clouds is an essential component in 3D scene analysis, but it poses several challenges, primarily due to the non-Euclidean nature of 3D point clouds. Although, several deep learning based approaches have been proposed to address this task, but almost all of them emphasized on using the latent (global) feature representations from traditional convolutional neural networks (CNN), resulting in severe loss of spatial information, thus failing to model the geometry of the underlying 3D objects, that plays an important role in remote sensing 3D scenes. In this l…
The robustness of semantic segmentation on edge cases of traffic scene is a vital factor for the safety of intelligent transportation. However, most of the critical scenes of traffic accidents are extremely dynamic and previously unseen, which seriously harm the performance of semantic segmentation methods. In addition, the delay of the traditional camera during high-speed driving will further reduce the contextual information in the time dimension. Therefore, we propose to extract dynamic context from event-based data with a higher temporal resolution to enhance static RGB images, even for th…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are trained only on instance-level pretext tasks, leading to representations that may be sub-optimal for downstream tasks requiring dense pixel predictions. In this paper, we introduce pixel-level pretext tasks for learning dense feature representations. The first task directly applies contrastive learning at the pixel level. We additionally propose a pixel-to-propag…
Current semantic segmentation methods focus only on mining "local" context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilated convolution, neural attention) or structure-aware optimization criteria (e.g., IoU-like loss). However, they ignore "global" context of the training data, i.e., rich semantic relations between pixels across different images. Inspired by the recent advance in unsupervised contrastive representation learning, we propose a pixel-wise contrastive framework for semantic segmentation in the fully supervised setting. The …
South China University of Technology（华南理工大学）；Central South University（中南大学）；Peking University（北京大学）；Southwest Jiaotong University（西南交通大学）
A critical challenge problem of scene change detection is that noisy changes generated by varying illumination, shadows and camera viewpoint make variances of a scene difficult to define and measure since the noisy changes and semantic ones are entangled. Following the intuitive idea of detecting changes by directly comparing dissimilarities between a pair of features, we propose a novel fully Convolutional siamese metric Network(CosimNet) to measure changes by customizing implicit metrics. To learn more discriminative metrics, we utilize contrastive loss to reduce the distance between the unc…
In the field of visual representation learning, performance of contrastive learning has been catching up with the supervised method which is commonly a classification convolutional neural network. However, most of the research work focuses on improving the accuracy of downstream tasks such as image classification and object detection. For visual contrastive learning, the influences of individual image features (e.g., color and shape) to model performance remain ambiguous. This paper investigates such influences by designing various ablation experiments, the results of which are evaluated by sp…
Scene understanding is crucial for autonomous systems which intend to operate in the real world. Single task vision networks extract information only based on some aspects of the scene. In multi-task learning (MTL), on the other hand, these single tasks are jointly learned, thereby providing an opportunity for tasks to share information and obtain a more comprehensive understanding. To this end, we develop UniNet, a unified scene understanding network that accurately and efficiently infers vital vision tasks including object detection, semantic segmentation, instance segmentation, monocular de…
University of Hong Kong（香港大学）；MEGVII Technology（旷视科技）；University of Edinburgh（爱丁堡大学）；LunarAI
In this paper, we tackle the problem of learning visual representations from unlabeled scene-centric data. Existing works have demonstrated the potential of utilizing the underlying complex structure within scene-centric data; still, they commonly rely on hand-crafted objectness priors or specialized pretext tasks to build a learning framework, which may harm generalizability. Instead, we propose contrastive learning from data-driven semantic slots, namely SlotCon, for joint semantic grouping and representation learning. The semantic grouping is performed by assigning pixels to a set of learna…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））
Estimating the motion of the camera together with the 3D structure of the scene from a monocular vision system is a complex task that often relies on the so-called scene rigidity assumption. When observing a dynamic environment, this assumption is violated which leads to an ambiguity between the ego-motion of the camera and the motion of the objects. To solve this problem, we present a self-supervised learning framework for 3D object motion field estimation from monocular videos. Our contributions are two-fold. First, we propose a two-stage projection pipeline to explicitly disentangle the cam…
Technical Report for ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Exploring Query-Based Segmentation and Increased Spatial Context for Outdoor Scene Understanding
Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still needs human cleaning. Directly learning representations from less-curated scene images is essential for pushing self-supervised learning to a higher level. Different from curated images which include simple and clear semantic information, scene images are more complex and mosaic because they often include complex scenes and multiple objects. Despite being feasible, recent works largely overlooked discovering the mos…
Recently, contrastive learning-based image translation methods have been proposed, which contrasts different spatial locations to enhance the spatial correspondence. However, the methods often ignore the diverse semantic relation within the images. To address this, here we propose a novel semantic relation consistency (SRC) regularization along with the decoupled contrastive learning, which utilize the diverse semantics by focusing on the heterogeneous semantics between the image patches of a single image. To further improve the performance, we present a hard negative mining by exploiting the …
Self-supervised contrastive learning has demonstrated great potential in learning visual representations. Despite their success in various downstream tasks such as image classification and object detection, self-supervised pre-training for fine-grained scenarios is not fully explored. We point out that current contrastive methods are prone to memorizing background/foreground texture and therefore have a limitation in localizing the foreground object. Analysis suggests that learning to extract discriminative texture information and localization are equally crucial for fine-grained self-supervis…
Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Research Center of Artificial Intelligence, Peng Cheng Laboratory（鹏城实验室人工智能研究中心）
Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation
Institute of Data Science (IDS)（数据科学研究所）；National University of Singapore（新加坡国立大学）；Nanyang Technological University (NTU)（南洋理工大学）；Tongji University（同济大学）
Scenes play a crucial role in breaking the storyline of movies and TV episodes into semantically cohesive parts. However, given their complex temporal structure, finding scene boundaries can be a challenging task requiring large amounts of labeled training data. To address this challenge, we present a self-supervised shot contrastive learning approach (ShotCoL) to learn a shot representation that maximizes the similarity between nearby shots compared to randomly selected shots. We show how to apply our learned shot representation for the task of scene boundary detection to offer state-of-the-a…
Tsinghua University（清华大学）；OpenAI；Peking University（北京大学）；KAUST（阿卜杜拉国王科技大学）；Mila（米拉）；University of California, Merced（加州大学默塞德分校）；Google Research（谷歌研究院）
Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images. Most existing methods address this challenge by using scene layouts, which are image-like representations of scene graphs designed to capture the coarse structures of scene images. Because scene layouts are manually crafted, the alignment with images may not be fully optimized, causing suboptimal compliance between the generated images and the original scene graphs. To tackle this issue, we pr…
Dual Contrastive Network for Few-Shot Remote Sensing Image Scene Classification
School of Electrical and Information Engineering, Tianjin University（天津大学电气与信息工程学院）；CETC Key Laboratory of Aerospace Information Applications（中国电子科技集团公司第五研究院航空航天信息应用重点实验室）
Most scene graph parsers use a two-stage pipeline to detect visual relationships: the first stage detects entities, and the second predicts the predicate for each entity pair using a softmax distribution. We find that such pipelines, trained with only a cross entropy loss over predicate classes, suffer from two common errors. The first, Entity Instance Confusion, occurs when the model confuses multiple instances of the same type of entity (e.g. multiple cups). The second, Proximal Relationship Ambiguity, arises when multiple subject-predicate-object triplets appear in close proximity with the …
In recent years self-supervised learning has emerged as a promising candidate for unsupervised representation learning. In the visual domain its applications are mostly studied in the context of images of natural scenes. However, its applicability is especially interesting in specific areas, like remote sensing and medicine, where it is hard to obtain huge amounts of labeled data. In this work, we conduct an extensive analysis of the applicability of self-supervised learning in remote sensing image classification. We analyze the influence of the number and domain of images used for self-superv…
In recent years, many automobiles have been equipped with cameras, which have accumulated an enormous amount of video footage of driving scenes. Autonomous driving demands the highest level of safety, for which even unimaginably rare driving scenes have to be collected in training data to improve the recognition accuracy for specific scenes. However, it is prohibitively costly to find very few specific scenes from an enormous amount of videos. In this article, we show that proper video-to-video distances can be defined by focusing on ego-vehicle actions. It is well known that existing methods …
Self-supervised representation learning is a critical problem in computer vision, as it provides a way to pretrain feature extractors on large unlabeled datasets that can be used as an initialization for more efficient and effective training on downstream tasks. A promising approach is to use contrastive learning to learn a latent space where features are close for similar data samples and far apart for dissimilar ones. This approach has demonstrated tremendous success for pretraining both image and point cloud feature extractors, but it has been barely investigated for multi-modal RGB-D scans…
The University of Sydney（悉尼大学）；JD Explore Academy（京东探索研究院）
Point cloud segmentation is fundamental in understanding 3D environments. However, current 3D point cloud segmentation methods usually perform poorly on scene boundaries, which degenerates the overall segmentation performance. In this paper, we focus on the segmentation of scene boundaries. Accordingly, we first explore metrics to evaluate the segmentation performance on scene boundaries. To address the unsatisfactory performance on boundaries, we then propose a novel contrastive boundary learning (CBL) framework for point cloud segmentation. Specifically, the proposed CBL enhances feature dis…
Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often contextually biased to the spurious scene correlations of different objects or object and background, which may harm their generalization on the downstream tasks. To tackle the issue, we develop a novel object-aware contrastive learning framework that first (a) localizes objects in a self-supervised manner and then (b) debias scene correlations via appropriate data …
The Hong Kong University of Science and Technology（香港科技大学）；University of Technology Sydney（悉尼科技大学）
Contrastive Language-Image Pre-training (CLIP) learns rich representations via readily available supervision of natural language. It improves the performance of downstream vision tasks, including but not limited to the zero-shot, long tail, segmentation, retrieval, caption, and video. However, the visual explainability of CLIP is rarely studied, especially for the raw feature map. To provide visual explanations of its predictions, we propose the Image-Text Similarity Map (ITSM). Based on it, we surprisingly find that CLIP prefers the background regions than the foregrounds, and shows erroneous…
Beijing Institute of Technology（北京理工大学）；Nankai University（南开大学）；China Electronics Standardization Institute（中国电子技术标准化研究院）；AICFVE of Beijing Film Academy（北京电影学院数字影视动画创作与理论研究北京市重点实验室）
Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information. Stereo matching is a computer vision based approach for 3-D scene reconstruction. In this paper, we explore an improved stereo matching network, SLED-Net, in which a Single Long Encoder-Decoder is proposed to replace the stacked hourglass network in PSM-Net for better contextual information learning. We compare SLED-Net to state-of-the-art methods recently published, and demonstrate its superior …
