Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments

Grounded Situation Recognition (GSR) is capable of recognizing and interpreting visual scenes in a contextually intuitive way, yielding salient activities (verbs) and the involved entities (roles) depicted in images. In this work, we focus on the application of GSR in assisting people with visual impairments (PVI). However, precise localization information of detected objects is often required to navigate their surroundings confidently and make informed decisions. For the first time, we propose an Open Scene Understanding (OpenSU) system that aims to generate pixel-wise dense segmentation masks of involved entities instead of bounding boxes. Specifically, we build our OpenSU system on top of GSR by additionally adopting an efficient Segment Anything Model (SAM). Furthermore, to enhance the feature extraction and interaction between the encoder-decoder structure, we construct our OpenSU system using a solid pure transformer backbone to improve the performance of GSR. In order to accelerate the convergence, we replace all the activation functions within the GSR decoders with GELU, thereby reducing the training duration. In quantitative analysis, our model achieves state-of-the-art performance on the SWiG dataset. Moreover, through field testing on dedicated assistive technology datasets and application demonstrations, the proposed OpenSU system can be used to enhance scene understanding and facilitate the independent mobility of people with visual impairments. Our code will be available at https://github.com/RuipingL/OpenSU.

Towards Anytime Optical Flow Estimation with Event Cameras

Event cameras are capable of responding to log-brightness changes in microseconds. Its characteristic of producing responses only to the changing region is particularly suitable for optical flow estimation. In contrast to the super low-latency response speed of event cameras, existing datasets collected via event cameras, however, only provide limited frame rate optical flow ground truth, (e.g., at 10Hz), greatly restricting the potential of event-driven optical flow. To address this challenge, we put forward a high-frame-rate, low-latency event representation Unified Voxel Grid, sequentially fed into the network bin by bin. We then propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow with only low-frame-rate optical flow ground truth for supervision. The key component of our EVA-Flow is the stacked Spatiotemporal Motion Refinement (SMR) module, which predicts temporally-dense optical flow and enhances the accuracy via spatial-temporal motion refinement. The time-dense feature warping utilized in the SMR module provides implicit supervision for the intermediate optical flow. Additionally, we introduce the Rectified Flow Warp Loss (RFWL) for the unsupervised evaluation of intermediate optical flow in the absence of ground truth. This is, to the best of our knowledge, the first work focusing on anytime optical flow estimation via event cameras. A comprehensive variety of experiments on MVSEC, DESC, and our EVA-FlowSet demonstrates that EVA-Flow achieves competitive performance, super-low-latency (5ms), fastest inference (9.2ms), time-dense motion estimation (200Hz), and strong generalization. Our code will be available at https://github.com/Yaozhuwa/EVA-Flow.

Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers

High-quality panoramic images with a Field of View (FoV) of 360-degree are essential for contemporary panoramic computer vision tasks. However, conventional imaging systems come with sophisticated lens designs and heavy optical components. This disqualifies their usage in many mobile and wearable applications where thin and portable, minimalist imaging systems are desired. In this paper, we propose a Panoramic Computational Imaging Engine (PCIE) to address minimalist and high-quality panoramic imaging. With less than three spherical lenses, a Minimalist Panoramic Imaging Prototype (MPIP) is constructed based on the design of the Panoramic Annular Lens (PAL), but with low-quality imaging results due to aberrations and small image plane size. We propose two pipelines, i.e. Aberration Correction (AC) and Super-Resolution and Aberration Correction (SR&AC), to solve the image quality problems of MPIP, with imaging sensors of small and large pixel size, respectively. To provide a universal network for the two pipelines, we leverage the information from the Point Spread Function (PSF) of the optical system and design a PSF-aware Aberration-image Recovery Transformer (PART), in which the self-attention calculation and feature extraction are guided via PSF-aware mechanisms. We train PART on synthetic image pairs from simulation and put forward the PALHQ dataset to fill the gap of real-world high-quality PAL images for low-level vision. A comprehensive variety of experiments on synthetic and real-world benchmarks demonstrates the impressive imaging results of PCIE and the effectiveness of plug-and-play PSF-aware mechanisms. We further deliver heuristic experimental findings for minimalist and high-quality panoramic imaging. Our dataset and code will be available at https://github.com/zju-jiangqi/PCIE-PART.

LF-PGVIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras using Points and Geodesic Segments

In this paper, we propose LF-PGVIO, a Visual-Inertial-Odometry (VIO) framework for large Field-of-View (FoV) cameras with a negative plane using points and geodesic segments. Notoriously, when the FoV of a panoramic camera reaches the negative half-plane, the image cannot be unfolded into a single pinhole image. Moreover, if a traditional straight-line detection method is directly applied to the original panoramic image, it cannot be normally used due to the large distortions in the panoramas and remains under-explored in the literature. To address these challenges, we put forward LF-PGVIO, which can provide line constraints for cameras with large FoV, even for cameras with negative-plane FoV, and directly extract omnidirectional curve segments from the raw omnidirectional image. We propose an Omnidirectional Curve Segment Detection (OCSD) method combined with a camera model which is applicable to images with large distortions, such as panoramic annular images, fisheye images, and various panoramic images. Each point on the image is projected onto the sphere, and the detected omnidirectional curve segments in the image named geodesic segments must satisfy the criterion of being a geodesic segment on the unit sphere. The detected geodesic segment is sliced into multiple straight-line segments according to the radian of the geodesic, and descriptors are extracted separately and recombined to obtain new descriptors. Based on descriptor matching, we obtain the constraint relationship of the 3D line segments between multiple frames. In our VIO system, we use sliding window optimization using point feature residuals, line feature residuals, and IMU residuals. Our evaluation of the proposed system on public datasets demonstrates that LF-PGVIO outperforms state-of-the-art methods in terms of accuracy and robustness. Code will be open-sourced at https://github.com/flysoaryun/LF-PGVIO.

VPUFormer: Visual Prompt Unified Transformer for Interactive Image Segmentation

The integration of diverse visual prompts like clicks, scribbles, and boxes in interactive image segmentation could significantly facilitate user interaction as well as improve interaction efficiency. Most existing studies focus on a single type of visual prompt by simply concatenating prompts and images as input for segmentation prediction, which suffers from low-efficiency prompt representation and weak interaction issues. This paper proposes a simple yet effective Visual Prompt Unified Transformer (VPUFormer), which introduces a concise unified prompt representation with deeper interaction to boost the segmentation performance. Specifically, we design a Prompt-unified Encoder (PuE) by using Gaussian mapping to generate a unified one-dimensional vector for click, box, and scribble prompts, which well captures users' intentions as well as provides a denser representation of user prompts. In addition, we present a Prompt-to-Pixel Contrastive Loss (P2CL) that leverages user feedback to gradually refine candidate semantic features, aiming to bring image semantic features closer to the features that are similar to the user prompt, while pushing away those image semantic features that are dissimilar to the user prompt, thereby correcting results that deviate from expectations. On this basis, our approach injects prompt representations as queries into Dual-cross Merging Attention (DMA) blocks to perform a deeper interaction between image and query inputs. A comprehensive variety of experiments on seven challenging datasets demonstrates that the proposed VPUFormer with PuE, DMA, and P2CL achieves consistent improvements, yielding state-of-the-art segmentation performance. Our code will be made publicly available at https://github.com/XuZhang1211/VPUFormer.

Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning

Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in typical unsupervised domain adaptation methods. It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain. However, in the absence of source data and target labels, current solutions cannot sufficiently reduce the impact of domain shift and fully leverage the information from the target data. In this paper, we propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast (IAPC) learning. The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain. Specifically, considering the problem of domain shift in the prediction of the target domain by the source model, we put forward an importance-aware mechanism for the biased target prediction probability distribution to extract domain-invariant knowledge from the source model. We further introduce a prototype-contrast strategy, which includes a prototype-symmetric cross-entropy loss and a prototype-enhanced cross-entropy loss, to learn target intra-domain knowledge without relying on labels. A comprehensive variety of experiments on two domain adaptive semantic segmentation benchmarks demonstrates that the proposed end-to-end IAPC solution outperforms existing state-of-the-art methods. Code will be made publicly available at https://github.com/yihong-97/Source-free_IAPC.

FeatFSDA: Towards Few-shot Domain Adaptation for Video-based Activity Recognition

Domain adaptation is essential for activity recognition, as common spatiotemporal architectures risk overfitting due to increased parameters arising from the temporal dimension. Unsupervised domain adaptation methods have been extensively studied, yet, they require large-scale unlabeled data from the target domain. In this work, we address few-shot domain adaptation for video-based activity recognition (FSDA-AR), which leverages a very small amount of labeled target videos to achieve effective adaptation. This setting is attractive and promising for applications, as it requires recording and labeling only a few, or even a single example per class in the target domain, which often includes activities that are rare yet crucial to recognize. We construct FSDA-AR benchmarks using five established datasets: UCF101, HMDB51, EPIC-KITCHEN, Sims4Action, and Toyota Smart Home. Our results demonstrate that FSDA-AR performs comparably to unsupervised domain adaptation with significantly fewer (yet labeled) target examples. We further propose a novel approach, FeatFSDA, to better leverage the few labeled target domain samples as knowledge guidance. FeatFSDA incorporates a latent space semantic adjacency loss, a domain prototypical similarity loss, and a graph-attentive-network-based edge dropout technique. Our approach achieves state-of-the-art performance on all datasets within our FSDA-AR benchmark. To encourage future research of few-shot domain adaptation for video-based activity recognition, we will release our benchmarks and code at https://github.com/KPeng9510/FeatFSDA.

SSD-MonoDTR: Supervised Scale-constrained Deformable Transformer for Monocular 3D Object Detection

Transformer-based methods have demonstrated superior performance for monocular 3D object detection recently, which predicts 3D attributes from a single 2D image. Most existing transformer-based methods leverage visual and depth representations to explore valuable query points on objects, and the quality of the learned queries has a great impact on detection accuracy. Unfortunately, existing unsupervised attention mechanisms in transformer are prone to generate low-quality query features due to inaccurate receptive fields, especially on hard objects. To tackle this problem, this paper proposes a novel ``Supervised Scale-constrained Deformable Attention'' (SSDA) for monocular 3D object detection. Specifically, SSDA presets several masks with different scales and utilizes depth and visual features to predict the local feature for each query. Imposing the scale constraint, SSDA could well predict the accurate receptive field of a query to support robust query feature generation. What is more, SSDA is assigned with a Weighted Scale Matching (WSM) loss to supervise scale prediction, which presents more confident results as compared to the unsupervised attention mechanisms. Extensive experiments on ``KITTI'' demonstrate that SSDA significantly improves the detection accuracy especially on moderate and hard objects, yielding SOTA performance as compared to the existing approaches. Code will be publicly available at https://github.com/mikasa3lili/SSD-MonoDETR.

AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation

Interactive Image Segmentation (IIS) has emerged as a promising technique for decreasing annotation time. Substantial progress has been made in pre- and post-processing for IIS, but the critical issue of interaction ambiguity notably hindering segmentation quality, has been under-researched. To address this, we introduce AdaptiveClick -- a clicks-aware transformer incorporating an adaptive focal loss, which tackles annotation inconsistencies with tools for mask- and pixel-level ambiguity resolution. To the best of our knowledge, AdaptiveClick is the first transformer-based, mask-adaptive segmentation framework for IIS. The key ingredient of our method is the Clicks-aware Mask-adaptive Transformer Decoder (CAMD), which enhances the interaction between clicks and image features. Additionally, AdaptiveClick enables pixel-adaptive differentiation of hard and easy samples in the decision space, independent of their varying distributions. This is primarily achieved by optimizing a generalized Adaptive Focal Loss (AFL) with a theoretical guarantee, where two adaptive coefficients control the ratio of gradient values for hard and easy pixels. Our analysis reveals that the commonly used Focal and BCE losses can be considered special cases of the proposed AFL loss. With a plain ViT backbone, extensive experimental results on nine datasets demonstrate the superiority of AdaptiveClick compared to state-of-the-art methods. Code will be publicly available at https://github.com/lab206/AdaptiveClick.

Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Driving

A semantic map of the road scene, covering fundamental road elements, is an essential ingredient in autonomous driving systems. It provides important perception foundations for positioning and planning when rendered in the Bird's-Eye-View (BEV). Currently, the prior knowledge of hypothetical depth can guide the learning of translating front perspective views into BEV directly with the help of calibration parameters. However, it suffers from geometric distortions in the representation of distant objects. In addition, another stream of methods without prior knowledge can learn the transformation between front perspective views and BEV implicitly with a global view. Considering that the fusion of different learning methods may bring surprising beneficial effects, we propose a Bi-Mapper framework for top-down road-scene semantic understanding, which incorporates a global view and local prior knowledge. To enhance reliable interaction between them, an asynchronous mutual learning strategy is proposed. At the same time, an Across-Space Loss (ASL) is designed to mitigate the negative impact of geometric distortions. Extensive results on nuScenes and Cam2BEV datasets verify the consistent effectiveness of each module in the proposed Bi-Mapper framework. Compared with exiting road mapping networks, the proposed Bi-Mapper achieves 5.0 higher IoU on the nuScenes dataset. Moreover, we verify the generalization performance of Bi-Mapper in a real-world driving scenario. Code will be available at https://github.com/lynn-yu/Bi-Mapper.