Vision-Language models like CLIP have been widely adopted for various tasks due to their impressive zero-shot capabilities. However, CLIP is not suitable for extracting 3D geometric features as it was trained on only images and text by natural language supervision. We work on addressing this limitation and propose a new framework termed CG3D (CLIP Goes 3D) where a 3D encoder is learned to exhibit zero-shot capabilities. CG3D is trained using triplets of pointclouds, corresponding rendered 2D images, and texts using natural language supervision. To align the features in a multimodal embedding space, we utilize contrastive loss on 3D features obtained from the 3D encoder, as well as visual and text features extracted from CLIP. We note that the natural images used to train CLIP and the rendered 2D images in CG3D have a distribution shift. Attempting to train the visual and text encoder to account for this shift results in catastrophic forgetting and a notable decrease in performance. To solve this, we employ prompt tuning and introduce trainable parameters in the input space to shift CLIP towards the 3D pre-training dataset utilized in CG3D. We extensively test our pre-trained CG3D framework and demonstrate its impressive capabilities in zero-shot, open scene understanding, and retrieval tasks. Further, it also serves as strong starting weights for fine-tuning in downstream 3D recognition tasks.
Solving multiple visual tasks using individual models can be resource-intensive, while multi-task learning can conserve resources by sharing knowledge across different tasks. Despite the benefits of multi-task learning, such techniques can struggle with balancing the loss for each task, leading to potential performance degradation. We present a novel computation- and parameter-sharing framework that balances efficiency and accuracy to perform multiple visual tasks utilizing individually-trained single-task transformers. Our method is motivated by transfer learning schemes to reduce computational and parameter storage costs while maintaining the desired performance. Our approach involves splitting the tasks into a base task and the other sub-tasks, and sharing a significant portion of activations and parameters/weights between the base and sub-tasks to decrease inter-task redundancies and enhance knowledge sharing. The evaluation conducted on NYUD-v2 and PASCAL-context datasets shows that our method is superior to the state-of-the-art transformer-based multi-task learning techniques with higher accuracy and reduced computational resources. Moreover, our method is extended to video stream inputs, further reducing computational costs by efficiently sharing information across the temporal domain as well as the task domain. Our codes and models will be publicly available.
In recent years, compact and efficient scene understanding representations have gained popularity in increasing situational awareness and autonomy of robotic systems. In this work, we illustrate the concept of a panoptic edge segmentation and propose PENet, a novel detection network called that combines semantic edge detection and instance-level perception into a compact panoptic edge representation. This is obtained through a joint network by multi-task learning that concurrently predicts semantic edges, instance centers and offset flow map without bounding box predictions exploiting the cross-task correlations among the tasks. The proposed approach allows extending semantic edge detection to panoptic edge detection which encapsulates both category-aware and instance-aware segmentation. We validate the proposed panoptic edge segmentation method and demonstrate its effectiveness on the real-world Cityscapes dataset.
3D scene understanding plays a vital role in vision-based autonomous driving. While most existing methods focus on 3D object detection, they have difficulty describing real-world objects of arbitrary shapes and infinite classes. Towards a more comprehensive perception of a 3D scene, in this paper, we propose a SurroundOcc method to predict the 3D occupancy with multi-camera images. We first extract multi-scale features for each image and adopt spatial 2D-3D attention to lift them to the 3D volume space. Then we apply 3D convolutions to progressively upsample the volume features and impose supervision on multiple levels. To obtain dense occupancy prediction, we design a pipeline to generate dense occupancy ground truth without expansive occupancy annotations. Specifically, we fuse multi-frame LiDAR scans of dynamic objects and static scenes separately. Then we adopt Poisson Reconstruction to fill the holes and voxelize the mesh to get dense occupancy labels. Extensive experiments on nuScenes and SemanticKITTI datasets demonstrate the superiority of our method. Code and dataset are available at https://github.com/weiyithu/SurroundOcc
Masked Autoencoders learn strong visual representations and achieve state-of-the-art results in several independent modalities, yet very few works have addressed their capabilities in multi-modality settings. In this work, we focus on point cloud and RGB image data, two modalities that are often presented together in the real world, and explore their meaningful interactions. To improve upon the cross-modal synergy in existing works, we propose PiMAE, a self-supervised pre-training framework that promotes 3D and 2D interaction through three aspects. Specifically, we first notice the importance of masking strategies between the two sources and utilize a projection module to complementarily align the mask and visible tokens of the two modalities. Then, we utilize a well-crafted two-branch MAE pipeline with a novel shared decoder to promote cross-modality interaction in the mask tokens. Finally, we design a unique cross-modal reconstruction module to enhance representation learning for both modalities. Through extensive experiments performed on large-scale RGB-D scene understanding benchmarks (SUN RGB-D and ScannetV2), we discover it is nontrivial to interactively learn point-image features, where we greatly improve multiple 3D detectors, 2D detectors, and few-shot classifiers by 2.9%, 6.7%, and 2.4%, respectively. Code is available at https://github.com/BLVLab/PiMAE.
Contrastive learning has recently demonstrated great potential for unsupervised pre-training in 3D scene understanding tasks. However, most existing work randomly selects point features as anchors while building contrast, leading to a clear bias toward background points that often dominate in 3D scenes. Also, object awareness and foreground-to-background discrimination are neglected, making contrastive learning less effective. To tackle these issues, we propose a general foreground-aware feature contrast FAC++ framework to learn more effective point cloud representations in pre-training. FAC++ consists of two novel contrast designs to construct more effective and informative contrast pairs. The first is building positive pairs within the same foreground segment where points tend to have the same semantics. The second is that we prevent over-discrimination between 3D segments/objects and encourage grouped foreground-to-background distinctions at the segment level with adaptive feature learning in a Siamese correspondence network, which adaptively learns feature correlations within and across point cloud views effectively. Moreover, we have designed the foreground-prompted regional sampling to enhance more balanced foreground-aware learning, which is termed FAC++. Visualization with point activation maps shows that our contrast pairs capture clear correspondences among foreground regions during pre-training. Quantitative experiments also show that FAC++ achieves superior knowledge transfer and data efficiency in various downstream 3D semantic segmentation, instance segmentation as well as object detection tasks. All codes, data, and models are available at: https://github.com/KangchengLiu/FAC_Foreground_Aware_Contrast
Traffic scene perception in computer vision is a critically important task to achieve intelligent cities. To date, most existing datasets focus on autonomous driving scenes. We observe that the models trained on those driving datasets often yield unsatisfactory results on traffic monitoring scenes. However, little effort has been put into improving the traffic monitoring scene understanding, mainly due to the lack of specific datasets. To fill this gap, we introduce a specialized traffic monitoring dataset, termed TSP6K, containing images from the traffic monitoring scenario, with high-quality pixel-level and instance-level annotations. The TSP6K dataset captures more crowded traffic scenes with several times more traffic participants than the existing driving scenes. We perform a detailed analysis of the dataset and comprehensively evaluate previous popular scene parsing methods, instance segmentation methods and unsupervised domain adaption methods. Furthermore, considering the vast difference in instance sizes, we propose a detail refining decoder for scene parsing, which recovers the details of different semantic regions in traffic scenes owing to the proposed TSP6K dataset. Experiments show its effectiveness in parsing the traffic monitoring scenes. Code and dataset are available at https://github.com/PengtaoJiang/TSP6K.
The ideal form of Visual Question Answering requires understanding, grounding and reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most existing VQA benchmarks are limited to just picking the answer from a pre-defined set of options and lack attention to text. We present a new challenge with a dataset that contains 23,781 questions based on 10124 image-text pairs. Specifically, the task requires the model to align multimedia representations of the same entity to implement multi-hop reasoning between image and text and finally use natural language to answer the question. The aim of this challenge is to develop and benchmark models that are capable of multimedia entity alignment, multi-step reasoning and open-ended answer generation.
Event cameras are bio-inspired sensors that capture the per-pixel intensity changes asynchronously and produce event streams encoding the time, pixel position, and polarity (sign) of the intensity changes. Event cameras possess a myriad of advantages over canonical frame-based cameras, such as high temporal resolution, high dynamic range, low latency, etc. Being capable of capturing information in challenging visual conditions, event cameras have the potential to overcome the limitations of frame-based cameras in the computer vision and robotics community. In very recent years, deep learning (DL) has been brought to this emerging field and inspired active research endeavors in mining its potential. However, there is still a lack of taxonomies in DL techniques for event-based vision. We first scrutinize the typical event representations with quality enhancement methods as they play a pivotal role as inputs to the DL models. We then provide a comprehensive survey of existing DL-based methods by structurally grouping them into two major categories: 1) image/video reconstruction and restoration; 2) event-based scene understanding and 3D vision. We conduct benchmark experiments for the existing methods in some representative research directions, i.e., image reconstruction, deblurring, and object recognition, to identify some critical insights and problems. Finally, we have discussions regarding the challenges and provide new perspectives for inspiring more research studies.
The ability to perceive and understand 3D scenes is crucial for many applications in computer vision and robotics. Inverse graphics is an appealing approach to 3D scene understanding that aims to infer the 3D scene structure from 2D images. In this paper, we introduce probabilistic modeling to the inverse graphics framework to quantify uncertainty and achieve robustness in 6D pose estimation tasks. Specifically, we propose 3D Neural Embedding Likelihood (3DNEL) as a unified probabilistic model over RGB-D images, and develop efficient inference procedures on 3D scene descriptions. 3DNEL effectively combines learned neural embeddings from RGB with depth information to improve robustness in sim-to-real 6D object pose estimation from RGB-D images. Performance on the YCB-Video dataset is on par with state-of-the-art yet is much more robust in challenging regimes. In contrast to discriminative approaches, 3DNEL's probabilistic generative formulation jointly models multiple objects in a scene, quantifies uncertainty in a principled way, and handles object pose tracking under heavy occlusion. Finally, 3DNEL provides a principled framework for incorporating prior knowledge about the scene and objects, which allows natural extension to additional tasks like camera pose tracking from video.
Synthesizing high-fidelity complex images from text is challenging. Based on large pretraining, the autoregressive and diffusion models can synthesize photo-realistic images. Although these large models have shown notable progress, there remain three flaws. 1) These models require tremendous training data and parameters to achieve good performance. 2) The multi-step generation design slows the image synthesis process heavily. 3) The synthesized visual features are difficult to control and require delicately designed prompts. To enable high-quality, efficient, fast, and controllable text-to-image synthesis, we propose Generative Adversarial CLIPs, namely GALIP. GALIP leverages the powerful pretrained CLIP model both in the discriminator and generator. Specifically, we propose a CLIP-based discriminator. The complex scene understanding ability of CLIP enables the discriminator to accurately assess the image quality. Furthermore, we propose a CLIP-empowered generator that induces the visual concepts from CLIP through bridge features and prompts. The CLIP-integrated generator and discriminator boost training efficiency, and as a result, our model only requires about 3% training data and 6% learnable parameters, achieving comparable results to large pretrained autoregressive and diffusion models. Moreover, our model achieves 120 times faster synthesis speed and inherits the smooth latent space from GAN. The extensive experimental results demonstrate the excellent performance of our GALIP. Code is available at https://github.com/tobran/GALIP.
In this paper, we consider the problem of simultaneously detecting objects and inferring their visual attributes in an image, even for those with no manual annotations provided at the training stage, resembling an open-vocabulary scenario. To achieve this goal, we make the following contributions: (i) we start with a naive two-stage approach for open-vocabulary object detection and attribute classification, termed CLIP-Attr. The candidate objects are first proposed with an offline RPN and later classified for semantic category and attributes; (ii) we combine all available datasets and train with a federated strategy to finetune the CLIP model, aligning the visual representation with attributes, additionally, we investigate the efficacy of leveraging freely available online image-caption pairs under weakly supervised learning; (iii) in pursuit of efficiency, we train a Faster-RCNN type model end-to-end with knowledge distillation, that performs class-agnostic object proposals and classification on semantic categories and attributes with classifiers generated from a text encoder; Finally, (iv) we conduct extensive experiments on VAW, MS-COCO, LSA, and OVAD datasets, and show that recognition of semantic category and attributes is complementary for visual scene understanding, i.e., jointly training object detection and attributes prediction largely outperform existing approaches that treat the two tasks independently, demonstrating strong generalization ability to novel attributes and categories.
Deep learning based pipelines for semantic segmentation often ignore structural information available on annotated images used for training. We propose a novel post-processing module enforcing structural knowledge about the objects of interest to improve segmentation results provided by deep learning. This module corresponds to a "many-to-one-or-none" inexact graph matching approach, and is formulated as a quadratic assignment problem. Our approach is compared to a CNN-based segmentation (for various CNN backbones) on two public datasets, one for face segmentation from 2D RGB images (FASSEG), and the other for brain segmentation from 3D MRIs (IBSR). Evaluations are performed using two types of structural information (distances and directional relations, , this choice being a hyper-parameter of our generic framework). On FASSEG data, results show that our module improves accuracy of the CNN by about 6.3% (the Hausdorff distance decreases from 22.11 to 20.71). On IBSR data, the improvement is of 51% (the Hausdorff distance decreases from 11.01 to 5.4). In addition, our approach is shown to be resilient to small training datasets that often limit the performance of deep learning methods: the improvement increases as the size of the training dataset decreases.
We introduce SceneDiffuser, a conditional generative model for 3D scene understanding. SceneDiffuser provides a unified model for solving scene-conditioned generation, optimization, and planning. In contrast to prior works, SceneDiffuser is intrinsically scene-aware, physics-based, and goal-oriented. With an iterative sampling strategy, SceneDiffuser jointly formulates the scene-aware generation, physics-based optimization, and goal-oriented planning via a diffusion-based denoising process in a fully differentiable fashion. Such a design alleviates the discrepancies among different modules and the posterior collapse of previous scene-conditioned generative models. We evaluate SceneDiffuser with various 3D scene understanding tasks, including human pose and motion generation, dexterous grasp generation, path planning for 3D navigation, and motion planning for robot arms. The results show significant improvements compared with previous models, demonstrating the tremendous potential of SceneDiffuser for the broad community of 3D scene understanding.
Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP to help the learning in 3D scene understanding has yet to be explored. In this paper, we make the first attempt to investigate how CLIP knowledge benefits 3D scene understanding. We propose CLIP2Scene, a simple yet effective framework that transfers CLIP knowledge from 2D image-text pre-trained models to a 3D point cloud network. We show that the pre-trained 3D network yields impressive performance on various downstream tasks, i.e., annotation-free and fine-tuning with labelled data for semantic segmentation. Specifically, built upon CLIP, we design a Semantic-driven Cross-modal Contrastive Learning framework that pre-trains a 3D network via semantic and spatial-temporal consistency regularization. For the former, we first leverage CLIP's text semantics to select the positive and negative point samples and then employ the contrastive loss to train the 3D network. In terms of the latter, we force the consistency between the temporally coherent point cloud features and their corresponding image features. We conduct experiments on SemanticKITTI, nuScenes, and ScanNet. For the first time, our pre-trained network achieves annotation-free 3D semantic segmentation with 20.8% and 25.08% mIoU on nuScenes and ScanNet, respectively. When fine-tuned with 1% or 100% labelled data, our method significantly outperforms other self-supervised methods, with improvements of 8% and 1% mIoU, respectively. Furthermore, we demonstrate the generalizability for handling cross-domain datasets. Code is publicly available https://github.com/runnanchen/CLIP2Scene.
Compositional representations of the world are a promising step towards enabling high-level scene understanding and efficient transfer to downstream tasks. Learning such representations for complex scenes and tasks remains an open challenge. Towards this goal, we introduce Neural Radiance Field Codebooks (NRC), a scalable method for learning object-centric representations through novel view reconstruction. NRC learns to reconstruct scenes from novel views using a dictionary of object codes which are decoded through a volumetric renderer. This enables the discovery of reoccurring visual and geometric patterns across scenes which are transferable to downstream tasks. We show that NRC representations transfer well to object navigation in THOR, outperforming 2D and 3D representation learning methods by 3.1% success rate. We demonstrate that our approach is able to perform unsupervised segmentation for more complex synthetic (THOR) and real scenes (NYU Depth) better than prior methods (29% relative improvement). Finally, we show that NRC improves on the task of depth ordering by 5.5% accuracy in THOR.
The past few years have witnessed the great success and prevalence of self-supervised representation learning within the language and 2D vision communities. However, such advancements have not been fully migrated to the field of 3D point cloud learning. Different from existing pre-training paradigms designed for deep point cloud feature extractors that fall into the scope of generative modeling or contrastive learning, this paper proposes a translative pre-training framework, namely PointVST, driven by a novel self-supervised pretext task of cross-modal translation from 3D point clouds to their corresponding diverse forms of 2D rendered images. More specifically, we begin with deducing view-conditioned point-wise embeddings through the insertion of the viewpoint indicator, and then adaptively aggregate a view-specific global codeword, which can be further fed into subsequent 2D convolutional translation heads for image generation. Extensive experimental evaluations on various downstream task scenarios demonstrate that our PointVST shows consistent and prominent performance superiority over current state-of-the-art approaches as well as satisfactory domain transfer capability. Our code will be publicly available at https://github.com/keeganhk/PointVST.
Curriculum learning and self-paced learning are the training strategies that gradually feed the samples from easy to more complex. They have captivated increasing attention due to their excellent performance in robotic vision. Most recent works focus on designing curricula based on difficulty levels in input samples or smoothing the feature maps. However, smoothing labels to control the learning utility in a curriculum manner is still unexplored. In this work, we design a paced curriculum by label smoothing (P-CBLS) using paced learning with uniform label smoothing (ULS) for classification tasks and fuse uniform and spatially varying label smoothing (SVLS) for semantic segmentation tasks in a curriculum manner. In ULS and SVLS, a bigger smoothing factor value enforces a heavy smoothing penalty in the true label and limits learning less information. Therefore, we design the curriculum by label smoothing (CBLS). We set a bigger smoothing value at the beginning of training and gradually decreased it to zero to control the model learning utility from lower to higher. We also designed a confidence-aware pacing function and combined it with our CBLS to investigate the benefits of various curricula. The proposed techniques are validated on four robotic surgery datasets of multi-class, multi-label classification, captioning, and segmentation tasks. We also investigate the robustness of our method by corrupting validation data into different severity levels. Our extensive analysis shows that the proposed method improves prediction accuracy and robustness.
Automatic video captioning aims for a holistic visual scene understanding. It requires a mechanism for capturing temporal context in video frames and the ability to comprehend the actions and associations of objects in a given timeframe. Such a system should additionally learn to abstract video sequences into sensible representations as well as to generate natural written language. While the majority of captioning models focus solely on the visual inputs, little attention has been paid to the audiovisual modality. To tackle this issue, we propose a novel two-fold approach. First, we implement a reward-guided KL Divergence to train a video captioning model which is resilient towards token permutations. Second, we utilise a Bi-Modal Hierarchical Reinforcement Learning (BMHRL) Transformer architecture to capture long-term temporal dependencies of the input data as a foundation for our hierarchical captioning module. Using our BMHRL, we show the suitability of the HRL agent in the generation of content-complete and grammatically sound sentences by achieving $4.91$, $2.23$, and $10.80$ in BLEU3, BLEU4, and METEOR scores, respectively on the ActivityNet Captions dataset. Finally, we make our BMHRL framework and trained models publicly available for users and developers at https://github.com/d-rothen/bmhrl.
Semi-supervised object detection is important for 3D scene understanding because obtaining large-scale 3D bounding box annotations on point clouds is time-consuming and labor-intensive. Existing semi-supervised methods usually employ teacher-student knowledge distillation together with an augmentation strategy to leverage unlabeled point clouds. However, these methods adopt global augmentation with scene-level transformations and hence are sub-optimal for instance-level object detection. In this work, we propose an object-level point augmentor (OPA) that performs local transformations for semi-supervised 3D object detection. In this way, the resultant augmentor is derived to emphasize object instances rather than irrelevant backgrounds, making the augmented data more useful for object detector training. Extensive experiments on the ScanNet and SUN RGB-D datasets show that the proposed OPA performs favorably against the state-of-the-art methods under various experimental settings. The source code will be available at https://github.com/nomiaro/OPA.