ICCV 2021 论文列表

Unprecedented access to multi-temporal satellite imagery has opened new perspectives for a variety of Earth observation tasks. Among them, pixel-precise panoptic segmentation of agricultural parcels has major economic and environmental implications. While researchers have explored this problem for single images, we argue that the complex temporal patterns of crop phenology are better addressed with temporal sequences of images. In this paper, we present the first end-to-end, single-stage method for panoptic segmentation of Satellite Image Time Series (SITS). This module can be combined with our novel image sequence encoding network which relies on temporal self-attention to extract rich and adaptive multi-scale spatio-temporal features. We also introduce PASTIS, the first open-access SITS dataset with panoptic annotations. We demonstrate the superiority of our encoder for semantic segmentation against multiple competing network architectures, and set up the first state-of-the-art of panoptic segmentation of SITS. Our implementation and the PASTIS dataset are publicly available at (link-upon-publication).

This paper proposes Panoptic Narrative Grounding, a spatially fine and general formulation of the natural language visual grounding problem. We establish an experimental framework for the study of this new task, including new ground truth and metrics, and we propose a strong baseline method to serve as stepping stone for future work. We exploit the intrinsic semantic richness in an image by including panoptic categories, and we approach visual grounding at a fine-grained level by using segmentations. In terms of ground truth, we propose an algorithm to automatically transfer Localized Narratives annotations to specific regions in the panoptic segmentations of the MS COCO dataset. To guarantee the quality of our annotations, we take advantage of the semantic structure contained in WordNet to exclusively incorporate noun phrases that are grounded to a meaningfully related panoptic segmentation region. The proposed baseline achieves a performance of 55.4 absolute Average Recall points. This result is a suitable foundation to push the envelope further in the development of methods for Panoptic Narrative Grounding.

360deg videos convey holistic views for the surroundings of a scene. It provides audio-visual cues beyond predetermined normal field of views and displays distinctive spatial relations on a sphere. However, previous benchmark tasks for panoramic videos are still limited to evaluate the semantic understanding of audio-visual relationships or spherical spatial property in surroundings. We propose a novel benchmark named Pano-AVQA as a large-scale grounded audio-visual question answering dataset on panoramic videos. Using 5.4K 360deg video clips harvested online, we collect two types of novel question-answer pairs with bounding-box grounding: spherical spatial relation QAs and audio-visual relation QAs. We train several transformer-based models from Pano-AVQA, where the results suggest that our proposed spherical spatial embeddings and multimodal training objectives fairly contribute to better semantic understanding of the panoramic surroundings on the dataset.

This paper studies the problem of painting the whole image from part of it, namely painting from part or part-painting for short, involving both inpainting and outpainting. To address the challenge of taking full advantage of both information from local domain (part) and knowledge from global domain (dataset), we propose a novel part-painting method according to the observations of relationship between part and whole, which consists of three stages: part-noise restarting, part-feature repainting, and part-patch refining, to paint the whole image by leveraging both feature-level and patch-level part as well as powerful representation ability of generative adversarial network. Extensive ablation studies show efficacy of each stage, and our method achieves state-of-the-art performance on both inpainting and outpainting benchmarks with free-form parts, including our new mask dataset for irregular outpainting. Our code and dataset are available at https://github.com/zhenglab/partpainting.

Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks. While reinforcement learning (RL) based agents can generate a stroke sequence step by step for this task, it is not easy to train a stable RL agent. On the other hand, stroke optimization methods search for a set of stroke parameters iteratively in a large search space; such low efficiency significantly limits their prevalence and practicality. Different from previous methods, in this paper, we formulate the task as a set prediction problem and propose a novel Transformer-based framework, dubbed Paint Transformer, to predict the parameters of a stroke set with a feed forward network. This way, our model can generate a set of strokes in parallel and obtain the final painting of size 512x512 in near real time. More importantly, since there is no dataset available for training the Paint Transformer, we devise a self-training pipeline such that it can be trained without any off-the-shelf dataset while still achieving excellent generalization capability. Experiments demonstrate that our method achieves better painting performance than previous ones with cheaper training and inference costs. Codes and models will be available.

Retrieving accurate 3D reconstructions of objects from the way they reflect light is a very challenging task in computer vision. Despite more than four decades since the definition of the Photometric Stereo problem, most of the literature has had limited success when global illumination effects such as cast shadows, self-reflections and ambient light come into play, especially for specular surfaces. Recent approaches have leveraged the capabilities of deep learning in conjunction with computer graphics in order to cope with the need of a vast number of training data to invert the image irradiance equation and retrieve the geometry of the object. However, rendering global illumination effects is a slow process which can limit the amount of training data that can be generated. In this work we propose a novel pixel-wise training procedure for normal prediction by replacing the training data (observation maps) of globally rendered images with independent per-pixel generated data. We show that global physical effects can be approximated on the observation map domain and this simplifies and speeds up the data creation procedure. Our network, PX-NET, achieves state-of-the-art performance compared to other pixelwise methods on synthetic datasets, as well as the DiLiGenT real dataset on both dense and sparse light settings.

High-quality point clouds have practical significance for point-based rendering, semantic understanding, and surface reconstruction. Upsampling sparse, noisy and non-uniform point clouds for a denser and more regular approximation of target objects is a desirable but challenging task. Most existing methods duplicate point features for upsampling, constraining the upsampling scales at a fixed rate. In this work, the arbitrary point clouds upsampling rates are achieved via edge-vector based affine combinations, and a novel design of Edge-Vector based Approximation for Flexible-scale Point clouds Upsampling (PU-EVA) is proposed. The edge-vector based approximation encodes neighboring connectivity via affine combinations based on edge vectors, and restricts the approximation error within a second-order term of Taylor's Expansion. Moreover, the EVA upsampling decouples the upsampling scales with network architecture, achieving the arbitrary upsampling rates in one-time training. Qualitative and quantitative evaluations demonstrate that the proposed PU-EVA outperforms the state-of-the-arts in terms of proximity-to-surface, distribution uniformity, and geometric details preservation.

Capsule Networks (CapsNets) create internal representations by parsing inputs into various instances at different resolution levels via a two-phase process -- part-whole transformation and hierarchical component routing. Since both of these internal phases are computationally expensive, CapsNets have not found wider use. Existing variations of CapsNets mainly focus on performance comparison with the original CapsNet, and have not outperformed CNN-based models on complex tasks. To address the limitations of the existing CapsNet structures, we propose a novel Prediction-Tuning Capsule Network (PT-CapsNet), and also introduce fully connected PT-Capsules (FC-PT-Caps) and locally connected PT-Capsules (LC-PT-Caps). Different from existing CapsNet structures, our proposed model (i) allows the use of capsules for more difficult vision tasks and provides wider applicability; and (ii) provides better than or comparable performance to CNN-based baselines on these complex tasks. In our experiments, we show robustness to affine transformations, as well as the lightweight and scalability of PT-CapsNet via constructing larger and deeper networks and performing comparisons on classification, semantic segmentation and object detection tasks. The results show consistent performance improvement and significant parameter reduction compared to various baseline models. Code is available at https://github.com/Christinepan881/PT-CapsNet.git.

We propose PR-RRN, a novel neural-network based method for Non-rigid Structure-from-Motion (NRSfM). PR-RRN consists of Residual-Recursive Networks (RRN) and two extra regularization losses. RRN is designed to effectively recover 3D shape and camera from 2D keypoints with novel residual-recursive structure. As NRSfM is a highly under-constrained problem, we propose two new pairwise regularization to further regularize the reconstruction. The Rigidity-based Pairwise Contrastive Loss regularizes the shape representation by encouraging higher similarity between the representations of high-rigidity pairs of frames than low-rigidity pairs. We propose minimum singular-value ratio to measure the pairwise rigidity. The Pairwise Consistency Loss enforces the reconstruction to be consistent when the estimated shapes and cameras are exchanged between pairs. Our approach achieves state-of-the-art performance on CMU MOCAP and PASCAL3D+ dataset.

Personalized video highlight detection aims to shorten a long video to interesting moments according to a user's preference, which has recently raised the community's attention. Current methods regard the user's history as holistic information to predict the user's preference but negating the inherent diversity of the user's interests, resulting in vague preference representation. In this paper, we propose a simple yet efficient preference reasoning framework (PR-Net) to explicitly take the diverse interests into account for frame-level highlight prediction. Specifically, distinct user-specific preferences for each input query frame are produced, presented as the similarity weighted sum of history highlights to the corresponding query frame. Next, distinct comprehensive preferences are formed by the user-specific preferences and a learnable generic preference for more overall highlight measurement. Lastly, the degree of highlight and non-highlight for each query frame is calculated as semantic similarity to its comprehensive and non-highlight preferences, respectively. Besides, to alleviate the ambiguity due to the incomplete annotation, a new bi-directional contrastive loss is proposed to ensure a compact and differentiable metric space. In this way, our method significantly outperforms state-of-the-art methods with a relative improvement of 12% in mean accuracy precision.

RGB-D based 6D pose estimation has recently achieved remarkable progress, but still suffers from two major limitations: (1) ineffective representation of depth data and (2) insufficient integration of different modalities. This paper proposes a novel deep learning approach, namely Graph Convolutional Network with Point Refinement (PR-GCN), to simultaneously address the issues above in a unified way. It first introduces the Point Refinement Network (PRN) to polish 3D point clouds, recovering missing parts with noise removed. Subsequently, the Multi-Modal Fusion Graph Convolutional Network (MMF-GCN) is presented to strengthen RGB-D combination, which captures geometry-aware inter-modality correlation through local information propagation in the graph convolutional network. Extensive experiments are conducted on three widely used benchmarks, and state-of-the-art performance is reached. Besides, it is also shown that the proposed PRN and MMF-GCN modules are well generalized to other frameworks.

Cross-domain object detection and semantic segmentation have witnessed impressive progress recently. Existing approaches mainly consider the domain shift resulting from external environments including the changes of background, illumination or weather, while distinct camera intrinsic parameters appear commonly in different domains and their influence for domain adaptation has been very rarely explored. In this paper, we observe that the Field of View (FoV) gap induces noticeable instance appearance differences between the source and target domains. We further discover that the FoV gap between two domains impairs domain adaptation performance under both the FoV-increasing (source FoV < target FoV) and FoV-decreasing cases. Motivated by the observations, we propose the Position-Invariant Transform (PIT) to better align images in different domains. We also introduce a reverse PIT for mapping the transformed/aligned images back to the original image space, and design a loss re-weighting strategy to accelerate the training process. Our method can be easily plugged into existing cross-domain detection/segmentation frameworks, while bringing about negligible computational overhead. Extensive experiments demonstrate that our method can soundly boost the performance on both cross-domain object detection and segmentation for state-of-the-art techniques. Our code is available at https://github.com/sheepooo/PIT-Position-Invariant-Transform.

Generating portrait images by controlling the motions of existing faces is an important task of great consequence to social media industries. For easy use and intuitive control, semantically meaningful and fully disentangled parameters should be used as modifications. However, many existing techniques do not provide such fine-grained controls or use indirect editing methods i.e. mimic motions of other individuals. In this paper, a Portrait Image Neural Renderer (PIRenderer) is proposed to control the face motions with the parameters of three-dimensional morphable face models (3DMMs). The proposed model can generate photo-realistic portrait images with accurate movements according to intuitive modifications. Experiments on both direct and indirect editing tasks demonstrate the superiority of this model. Meanwhile, we further extend this model to tackle the audio-driven facial reenactment task by extracting sequential motions from audio inputs. We show that our model can generate coherent videos with convincing movements from only a single reference image and a driving audio stream. Our source code is available at https://github.com/RenYurui/PIRender.

We present PICCOLO, a simple and efficient algorithm for omnidirectional localization. Given a colored point cloud and a 360 panorama image of a scene, our objective is to recover the camera pose at which the panorama image is taken. Our pipeline works in an off-the-shelf manner with a single image given as a query and does not require any training of neural networks or collecting ground-truth poses of images. Instead, we match each point cloud color to the holistic view of the panorama image with gradient-descent optimization to find the camera pose. Our loss function, called sampling loss, is point cloud-centric, evaluated at the projected location of every point in the point cloud. In contrast, conventional photometric loss is image-centric, comparing colors at each pixel location. With a simple change in the compared entities, sampling loss effectively overcomes the severe visual distortion of omnidirectional images, and enjoys the global context of the 360 view to handle challenging scenarios for visual localization. PICCOLO outperforms existing omnidirectional localization algorithms in both accuracy and stability when evaluated in various environments.

Facial Action Units (AUs) are of great significance in communication. Automatic AU detection can improve the understanding of psychological conditions and emotional status. Recently, several deep learning methods have been proposed to detect AUs automatically. However, several challenges, such as poor extraction of fine-grained and robust local AUs information, model overfitting on person-specific features, as well as the limitation of datasets with wrong labels, remain to be addressed. In this paper, we propose a joint strategy called PIAP-DF to solve these problems, which involves 1) a multi-stage Pixel-Interested learning method with pixel-level attention for each AU; 2) an Anti Person-Specific method aiming to eliminate features associated with any individual as much as possible; 3) a semi-supervised learning method with Discrete Feedback, designed to effectively utilize unlabeled data and mitigate the negative impacts of wrong labels. Experimental results on the two popular AU detection datasets BP4D and DISFA prove that PIAP-DF can be the new state-of-the-art method. Compared with the current best method, PIAP-DF improves the average F1 score by 3.2% on BP4D and by 0.5% on DISFA. All modules of PIAP-DF can be easily removed after training to obtain a lightweight model for practical application.

Rigid registration of point clouds with partial overlaps is a longstanding problem usually solved in two steps: (a) finding correspondences between the point clouds; (b) filtering these correspondences to keep only the most reliable ones to estimate the transformation. Recently, several deep nets have been proposed to solve these steps jointly. We built upon these works and propose PCAM: a neural network whose key element is a pointwise product of cross-attention matrices that permits to mix both low-level geometric and high-level contextual information to find point correspondences. These cross-attention matrices also permits the exchange of context information between the point clouds, at each layer, allowing the network construct better matching features within the overlapping regions. The experiments show that PCAM achieves state-of-the-art results among methods which, like us, solve steps (a) and (b) jointly via deepnets.

Face recognition networks encode information about sensitive attributes while being trained for identity classification. Such encoding has two major issues: (a) it makes the face representations susceptible to privacy leakage (b) it appears to contribute to bias in face recognition. However, existing bias mitigation approaches generally require end-to-end training and are unable to achieve high verification accuracy. Therefore, we present a descriptor-based adversarial de-biasing approach called `Protected Attribute Suppression System (PASS)'. PASS can be trained on top of descriptors obtained from any previously trained high-performing network to classify identities and simultaneously reduce encoding of sensitive attributes. This eliminates the need for end-to-end training. As a component of PASS, we present a novel discriminator training strategy that discourages a network from encoding protected attribute information. We show the efficacy of PASS to reduce gender and skintone information in descriptors from SOTA face recognition networks like Arcface. As a result, PASS descriptors outperform existing baselines in reducing gender and skintone bias on the IJB-C dataset, while maintaining a high verification accuracy.

From an early age, humans perceive the visual world as composed of coherent objects with distinctive properties such as shape, size, and color. There is great interest in building models that are able to learn similar structure, ideally in an unsupervised manner. Learning such structure from complex 3D scenes that include clutter, occlusions, interactions, and camera motion is still an open challenge. We present a model that is able to segment visual scenes from complex 3D environments into distinct objects, learn disentangled representations of individual objects, and form consistent and coherent predictions of future frames, in a fully unsupervised manner. Our model (named PARTS) builds on recent approaches that utilize iterative amortized inference and transition dynamics for deep generative models. We achieve dramatic improvements in performance by introducing several novel contributions. We introduce a recurrent slot-attention like encoder which allows for top-down influence during inference. Unlike prior work, we eschew using an auto-regressive prior when modeling image sequences, and demonstrate that a fixed frame-independent prior is superior for the purpose of scene segmentation and representation learning. We demonstrate our model's success on three different video datasets (the popular benchmark CLEVRER; a simulated 3D Playroom environment; and a real-world Robotics Arm dataset). Finally, we analyze the contributions of the various model components and the representations learned by the model.

Despite significant progress, we show that state of the art 3D human pose and shape estimation methods remain sensitive to partial occlusion and can produce dramatically wrong predictions although much of the body is observable. To address this, we introduce a soft attention mechanism, called the Part Attention REgressor (PARE), that learns to predict body-part-guided attention masks. We observe that state-of-the-art methods rely on global feature representations, making them sensitive to even small occlusions. In contrast, PARE's part-guided attention mechanism overcomes these issues by exploiting information about the visibility of individual body parts while leveraging information from neighboring body-parts to predict occluded parts. We show qualitatively that PARE learns sensible attention masks, and quantitative evaluation confirms that PARE achieves more accurate and robust reconstruction results than existing approaches on both occlusion-specific and standard benchmarks. The code and data are available for research purposes at https://pare.is.tue.mpg.de/