Yifan Liu

Wei Yin, Jianming Zhang, Oliver Wang et al.

Despite significant progress made in the past few years, challenges remain for depth estimation using a single monocular image. First, it is nontrivial to train a metric-depth prediction model that can generalize well to diverse scenes mainly due to limited training data. Thus, researchers have built large-scale relative depth datasets that are much easier to collect. However, existing relative depth estimation models often fail to recover accurate 3D scene shapes due to the unknown depth shift caused by training with the relative depth data. We tackle this problem here and attempt to estimate accurate scene shapes by training on large-scale relative depth data, and estimating the depth shift. To do so, we propose a two-stage framework that first predicts depth up to an unknown scale and shift from a single monocular image, and then exploits 3D point cloud data to predict the depth shift and the camera's focal length that allow us to recover 3D scene shapes. As the two modules are trained separately, we do not need strictly paired training data. In addition, we propose an image-level normalized regression loss and a normal-based geometry loss to improve training with relative depth annotation. We test our depth model on nine unseen datasets and achieve state-of-the-art performance on zero-shot evaluation. Code is available at: https://git.io/Depth

Muzhi Zhu, Hengtao Li, Hao Chen et al. · cmu

Current closed-set instance segmentation models rely on pre-defined class labels for each mask during training and evaluation, largely limiting their ability to detect novel objects. Open-world instance segmentation (OWIS) models address this challenge by detecting unknown objects in a class-agnostic manner. However, previous OWIS approaches completely erase category information during training to keep the model's ability to generalize to unknown objects. In this work, we propose a novel training mechanism termed SegPrompt that uses category information to improve the model's class-agnostic segmentation ability for both known and unknown categories. In addition, the previous OWIS training setting exposes the unknown classes to the training set and brings information leakage, which is unreasonable in the real world. Therefore, we provide a new open-world benchmark closer to a real-world scenario by dividing the dataset classes into known-seen-unseen parts. For the first time, we focus on the model's ability to discover objects that never appear in the training set images. Experiments show that SegPrompt can improve the overall and unseen detection performance by 5.6% and 6.1% in AR on our new benchmark without affecting the inference efficiency. We further demonstrate the effectiveness of our method on existing cross-dataset transfer and strongly supervised settings, leading to 5.5% and 12.3% relative improvement.

Changyong Shu, JIajun Deng, Fisher Yu et al.

Transformer-based methods have swept the benchmarks on 2D and 3D detection on images. Because tokenization before the attention mechanism drops the spatial information, positional encoding becomes critical for those methods. Recent works found that encodings based on samples of the 3D viewing rays can significantly improve the quality of multi-camera 3D object detection. We hypothesize that 3D point locations can provide more information than rays. Therefore, we introduce 3D point positional encoding, 3DPPE, to the 3D detection Transformer decoder. Although 3D measurements are not available at the inference time of monocular 3D object detection, 3DPPE uses predicted depth to approximate the real point positions. Our hybriddepth module combines direct and categorical depth to estimate the refined depth of each pixel. Despite the approximation, 3DPPE achieves 46.0 mAP and 51.4 NDS on the competitive nuScenes dataset, significantly outperforming encodings based on ray samples. We make the codes available at https://github.com/drilistbox/3DPPE.

Thomas E. Huang, Yifan Liu, Luc Van Gool et al. · eth-zurich

Performing multiple heterogeneous visual tasks in dynamic scenes is a hallmark of human perception capability. Despite remarkable progress in image and video recognition via representation learning, current research still focuses on designing specialized networks for singular, homogeneous, or simple combination of tasks. We instead explore the construction of a unified model for major image and video recognition tasks in autonomous driving with diverse input and output structures. To enable such an investigation, we design a new challenge, Video Task Decathlon (VTD), which includes ten representative image and video tasks spanning classification, segmentation, localization, and association of objects and pixels. On VTD, we develop our unified network, VTDNet, that uses a single structure and a single set of weights for all ten tasks. VTDNet groups similar tasks and employs task interaction stages to exchange information within and between task groups. Given the impracticality of labeling all tasks on all frames, and the performance degradation associated with joint training of many tasks, we design a Curriculum training, Pseudo-labeling, and Fine-tuning (CPF) scheme to successfully train VTDNet on all tasks and mitigate performance loss. Armed with CPF, VTDNet significantly outperforms its single-task counterparts on most tasks with only 20% overall computations. VTD is a promising new direction for exploring the unification of perception tasks in autonomous driving.

Jianlong Yuan, Qian Qi, Fei Du et al.

In this work, we explore data augmentations for knowledge distillation on semantic segmentation. To avoid over-fitting to the noise in the teacher network, a large number of training examples is essential for knowledge distillation. Imagelevel argumentation techniques like flipping, translation or rotation are widely used in previous knowledge distillation framework. Inspired by the recent progress on semantic directions on feature-space, we propose to include augmentations in feature space for efficient distillation. Specifically, given a semantic direction, an infinite number of augmentations can be obtained for the student in the feature space. Furthermore, the analysis shows that those augmentations can be optimized simultaneously by minimizing an upper bound for the losses defined by augmentations. Based on the observation, a new algorithm is developed for knowledge distillation in semantic segmentation. Extensive experiments on four semantic segmentation benchmarks demonstrate that the proposed method can boost the performance of current knowledge distillation methods without any significant overhead. Code is available at: https://github.com/jianlong-yuan/FAKD.

Jianlong Yuan, Jinchao Ge, Zhibin Wang et al.

Consistency regularization has been widely studied in recent semisupervised semantic segmentation methods, and promising performance has been achieved. In this work, we propose a new consistency regularization framework, termed mutual knowledge distillation (MKD), combined with data and feature augmentation. We introduce two auxiliary mean-teacher models based on consistency regularization. More specifically, we use the pseudo-labels generated by a mean teacher to supervise the student network to achieve a mutual knowledge distillation between the two branches. In addition to using image-level strong and weak augmentation, we also discuss feature augmentation. This involves considering various sources of knowledge to distill the student network. Thus, we can significantly increase the diversity of the training samples. Experiments on public benchmarks show that our framework outperforms previous state-of-the-art (SOTA) methods under various semi-supervised settings. Code is available at semi-mmseg.

Bowen Zhang, Zhi Tian, Quan Tang et al.

We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level representation from the output of the ViT. Differently, we make use of the fundamental component -- attention mechanism, to generate masks for semantic segmentation. Specifically, we propose the Attention-to-Mask (ATM) module, in which the similarity maps between a set of learnable class tokens and the spatial feature maps are transferred to the segmentation masks. Experiments show that our proposed SegVit using the ATM module outperforms its counterparts using the plain ViT backbone on the ADE20K dataset and achieves new state-of-the-art performance on COCO-Stuff-10K and PASCAL-Context datasets. Furthermore, to reduce the computational cost of the ViT backbone, we propose query-based down-sampling (QD) and query-based up-sampling (QU) to build a Shrunk structure. With the proposed Shrunk structure, the model can save up to $40\%$ computations while maintaining competitive performance.

Xuqian Ren, Yifan Liu

Previous harmonization methods focus on adjusting one inharmonious region in an image based on an input mask. They may face problems when dealing with different perturbations on different semantic regions without available input masks. To deal with the problem that one image has been pasted with several foregrounds coming from different images and needs to harmonize them towards different domain directions without any mask as input, we propose a new semantic-guided multi-mask image harmonization task. Different from the previous single-mask image harmonization task, each inharmonious image is perturbed with different methods according to the semantic segmentation masks. Two challenging benchmarks, HScene and HLIP, are constructed based on $150$ and $19$ semantic classes, respectively. Furthermore, previous baselines focus on regressing the exact value for each pixel of the harmonized images. The generated results are in the `black box' and cannot be edited. In this work, we propose a novel way to edit the inharmonious images by predicting a series of operator masks. The masks indicate the level and the position to apply a certain image editing operation, which could be the brightness, the saturation, and the color in a specific dimension. The operator masks provide more flexibility for users to edit the image further. Extensive experiments verify that the operator mask-based network can further improve those state-of-the-art methods which directly regress RGB images when the perturbations are structural. Experiments have been conducted on our constructed benchmarks to verify that our proposed operator mask-based framework can locate and modify the inharmonious regions in more complex scenes. Our code and models are available at https://github.com/XuqianRen/Semantic-guided-Multi-mask-Image-Harmonization.git.

Yichen Sheng, Yifan Liu, Jianming Zhang et al.

Shadows are essential for realistic image compositing. Physics-based shadow rendering methods require 3D geometries, which are not always available. Deep learning-based shadow synthesis methods learn a mapping from the light information to an object's shadow without explicitly modeling the shadow geometry. Still, they lack control and are prone to visual artifacts. We introduce pixel heigh, a novel geometry representation that encodes the correlations between objects, ground, and camera pose. The pixel height can be calculated from 3D geometries, manually annotated on 2D images, and can also be predicted from a single-view RGB image by a supervised approach. It can be used to calculate hard shadows in a 2D image based on the projective geometry, providing precise control of the shadows' direction and shape. Furthermore, we propose a data-driven soft shadow generator to apply softness to a hard shadow based on a softness input parameter. Qualitative and quantitative evaluations demonstrate that the proposed pixel height significantly improves the quality of the shadow generation while allowing for controllability.

Jiaxi Lv, Yi Huang, Mingfu Yan et al.

Recent advances in text-to-video generation have harnessed the power of diffusion models to create visually compelling content conditioned on text prompts. However, they usually encounter high computational costs and often struggle to produce videos with coherent physical motions. To tackle these issues, we propose GPT4Motion, a training-free framework that leverages the planning capability of large language models such as GPT, the physical simulation strength of Blender, and the excellent image generation ability of text-to-image diffusion models to enhance the quality of video synthesis. Specifically, GPT4Motion employs GPT-4 to generate a Blender script based on a user textual prompt, which commands Blender's built-in physics engine to craft fundamental scene components that encapsulate coherent physical motions across frames. Then these components are inputted into Stable Diffusion to generate a video aligned with the textual prompt. Experimental results on three basic physical motion scenarios, including rigid object drop and collision, cloth draping and swinging, and liquid flow, demonstrate that GPT4Motion can generate high-quality videos efficiently in maintaining motion coherency and entity consistency. GPT4Motion offers new insights in text-to-video research, enhancing its quality and broadening its horizon for further explorations.

Bingqing Zhang, Sen Wang, Yifan Liu et al.

Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame. This results in suboptimal performance and increased computational complexity. In this work, we propose an image-level Object Detection Difficulty (ODD) metric to quantify the difficulty of detecting objects in a given image. The derived ODD scores can be used in the VOD process to mitigate over-aggregation. Specifically, we train an ODD predictor as an auxiliary head of a still-image object detector to compute the ODD score for each image based on the discrepancies between detection results and ground-truth bounding boxes. The ODD score enhances the VOD system in two ways: 1) it enables the VOD system to select superior global reference frames, thereby improving overall accuracy; and 2) it serves as an indicator in the newly designed ODD Scheduler to eliminate the aggregation of frames that are easy to detect, thus accelerating the VOD process. Comprehensive experiments demonstrate that, when utilized for selecting global reference frames, ODD-VOD consistently enhances the accuracy of Global-frame-based VOD models. When employed for acceleration, ODD-VOD consistently improves the frames per second (FPS) by an average of 73.3% across 8 different VOD models without sacrificing accuracy. When combined, ODD-VOD attains state-of-the-art performance when competing with many VOD methods in both accuracy and speed. Our work represents a significant advancement towards making VOD more practical for real-world applications.

Yi Huang, Jiancheng Huang, Yifan Liu et al.

Denoising diffusion models have emerged as a powerful tool for various image generation and editing tasks, facilitating the synthesis of visual content in an unconditional or input-conditional manner. The core idea behind them is learning to reverse the process of gradually adding noise to images, allowing them to generate high-quality samples from a complex distribution. In this survey, we provide an exhaustive overview of existing methods using diffusion models for image editing, covering both theoretical and practical aspects in the field. We delve into a thorough analysis and categorization of these works from multiple perspectives, including learning strategies, user-input conditions, and the array of specific editing tasks that can be accomplished. In addition, we pay special attention to image inpainting and outpainting, and explore both earlier traditional context-driven and current multimodal conditional methods, offering a comprehensive analysis of their methodologies. To further evaluate the performance of text-guided image editing algorithms, we propose a systematic benchmark, EditEval, featuring an innovative metric, LMM Score. Finally, we address current limitations and envision some potential directions for future research. The accompanying repository is released at https://github.com/SiatMMLab/Awesome-Diffusion-Model-Based-Image-Editing-Methods.

Yifan Liu, Youbao Tang, Ning Zhang et al.

Temporal action localization (TAL) aims to detect the boundary and identify the class of each action instance in a long untrimmed video. Current approaches treat video frames homogeneously, and tend to give background and key objects excessive attention. This limits their sensitivity to localize action boundaries. To this end, we propose a prior-enhanced temporal action localization method (PETAL), which only takes in RGB input and incorporates action subjects as priors. This proposal leverages action subjects' information with a plug-and-play subject-aware spatial attention module (SA-SAM) to generate an aggregated and subject-prioritized representation. Experimental results on THUMOS-14 and ActivityNet-1.3 datasets demonstrate that the proposed PETAL achieves competitive performance using only RGB features, e.g., boosting mAP by 2.41% or 0.25% over the state-of-the-art approach that uses RGB features or with additional optical flow features on the THUMOS-14 dataset.

Yifan Liu, Fangneng Zhan, Kaichen Zhou et al.

Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding, which are crucial for real-world applications like robotics and embodied agents. We attribute this to a modality gap between the 3D tasks and the 2D training of VLM, which led to inefficient retrieval of 3D information from 2D input. To bridge this gap, we introduce SandboxVLM, a simple yet effective framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM. Specifically, we design a 3D Sandbox reconstruction and perception pipeline comprising four stages: generating multi-view priors with abstract control, proxy elevation, multi-view voting and clustering, and 3D-aware reasoning. Evaluated in zero-shot settings across multiple benchmarks and VLM backbones, our approach consistently improves spatial intelligence, achieving an 8.3\% gain on SAT Real compared with baseline methods for instance. These results demonstrate that equipping VLMs with a 3D abstraction substantially enhances their 3D reasoning ability without additional training, suggesting new possibilities for general-purpose embodied intelligence.

Yifan Liu, Xishun Liao, Haoxuan Ma et al.

Understanding and modeling human mobility patterns is crucial for effective transportation planning and urban development. Despite significant advances in mobility research, there remains a critical gap in simulation platforms that allow for algorithm development, policy implementation, and comprehensive evaluation at scale. Traditional activity-based models require extensive data collection and manual calibration, machine learning approaches struggle with adaptation to dynamic conditions, and treding agent-based Large Language Models (LLMs) implementations face computational constraints with large-scale simulations. To address these challenges, we propose MobiVerse, a hybrid framework leverages the efficiency of lightweight domain-specific generator for generating base activity chains with the adaptability of LLMs for context-aware modifications. A case study was conducted in Westwood, Los Angeles, where we efficiently generated and dynamically adjusted schedules for the whole population of approximately 53,000 agents on a standard PC. Our experiments demonstrate that MobiVerse successfully enables agents to respond to environmental feedback, including road closures, large gathering events like football games, and congestion, through our hybrid framework. Its modular design facilitates testing various mobility algorithms at both transportation system and agent levels. Results show our approach maintains computational efficiency while enhancing behavioral realism. MobiVerse bridges the gap in mobility simulation by providing a customizable platform for mobility systems planning and operations with benchmark algorithms. Code and videos are available at https://github.com/ucla-mobility/MobiVerse.

Yifan Liu, Yaokun Liu, Zelin Li et al.

Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via sequence-to-sequence modeling. However, these two stages are optimized for different objectives: semantic reconstruction during tokenizer pretraining versus user interaction modeling during recommender training. This objective misalignment leads to two key limitations: (i) suboptimal static tokenization, where fixed token assignments fail to reflect diverse usage contexts; and (ii) discarded pretrained semantics, where pretrained knowledge - typically from language model embeddings - is overwritten during recommender training on user interactions. To address these limitations, we propose to learn DEcomposed COntextual Token Representations (DECOR), a unified framework that preserves pretrained semantics while enhancing the adaptability of token embeddings. DECOR introduces contextualized token composition to refine token embeddings based on user interaction context, and decomposed embedding fusion that integrates pretrained codebook embeddings with newly learned collaborative embeddings. Experiments on three real-world datasets demonstrate that DECOR consistently outperforms state-of-the-art baselines in recommendation performance. Our code will be made available upon publication.

Yifan Liu, Chunhua Shen, Changqian Yu et al.

Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into account,e.g., by propagating the results to the neighboring frames using optical flow or extracting frame representations using multi-frame information, which may lead to inaccurate results or unbalanced latency. In this work, we focus on improving the temporal consistency without introducing computation overhead in inference. To this end, we perform inference at each frame. Temporal consistency is achieved by learning from video frames with extra constraints during the training phase. introduced for inference. We propose several techniques to learn from the video sequence, including a temporal consistency loss and online/offline knowledge distillation methods. On the task of semantic video segmentation, weighing among accuracy, temporal smoothness, and efficiency, our proposed method outperforms keyframe-based methods and a few baseline methods that are trained with each frame independently, on datasets including Cityscapes, Camvid, and 300VW-Mask. We further apply our training method to video instance segmentation on YouTubeVISand develop an application of portrait matting in video sequences, by segmenting temporally consistent instance-level trimaps across frames. Experiments show superior qualitative and quantitative results. Code is available at: https://git.io/vidseg.

Wei Yin, Yifan Liu, Chunhua Shen

Monocular depth prediction plays a crucial role in understanding 3D scene geometry. Although recent methods have achieved impressive progress in terms of evaluation metrics such as the pixel-wise relative error, most methods neglect the geometric constraints in the 3D space. In this work, we show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, namely, virtual normal directions determined by randomly sampled three points in the reconstructed 3D space, we significantly improve the accuracy and robustness of monocular depth estimation. Significantly, the virtual normal loss can not only improve the performance of learning metric depth, but also disentangle the scale information and enrich the model with better shape information. Therefore, when not having access to absolute metric depth training data, we can use virtual normal to learn a robust affine-invariant depth generated on diverse scenes. In experiments, We show state-of-the-art results of learning metric depth on NYU Depth-V2 and KITTI. From the high-quality predicted depth, we are now able to recover good 3D structures of the scene such as the point cloud and surface normal directly, eliminating the necessity of relying on additional models as was previously done. To demonstrate the excellent generalizability of learning affine-invariant depth on diverse data with the virtual normal loss, we construct a large-scale and diverse dataset for training affine-invariant depth, termed Diverse Scene Depth dataset (DiverseDepth), and test on five datasets with the zero-shot test setting. Code is available at: https://git.io/Depth

Changqian Yu, Yifan Liu, Changxin Gao et al.

Non-local operation is widely explored to model the long-range dependencies. However, the redundant computation in this operation leads to a prohibitive complexity. In this paper, we present a Representative Graph (RepGraph) layer to dynamically sample a few representative features, which dramatically reduces redundancy. Instead of propagating the messages from all positions, our RepGraph layer computes the response of one node merely with a few representative nodes. The locations of representative nodes come from a learned spatial offset matrix. The RepGraph layer is flexible to integrate into many visual architectures and combine with other operations. With the application of semantic segmentation, without any bells and whistles, our RepGraph network can compete or perform favourably against the state-of-the-art methods on three challenging benchmarks: ADE20K, Cityscapes, and PASCAL-Context datasets. In the task of object detection, our RepGraph layer can also improve the performance on the COCO dataset compared to the non-local operation. Code is available at https://git.io/RepGraph.

Yifan Liu, Chunhua Shen, Changqian Yu et al.

For semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence. Advanced methods take into considerations the correlations in the video sequence, e.g., by propagating the results to the neighboring frames using optical flow, or extracting the frame representations with other frames, which may lead to inaccurate results or unbalanced latency. In this work, we process efficient semantic video segmentation in a per-frame fashion during the inference process. Different from previous per-frame models, we explicitly consider the temporal consistency among frames as extra constraints during the training process and embed the temporal consistency into the segmentation network. Therefore, in the inference process, we can process each frame independently with no latency, and improve the temporal consistency with no extra computational cost and post-processing. We employ compact models for real-time execution. To narrow the performance gap between compact models and large models, new knowledge distillation methods are designed. Our results outperform previous keyframe based methods with a better trade-off between the accuracy and the inference speed on popular benchmarks, including the Cityscapes and Camvid. The temporal consistency is also improved compared with corresponding baselines which are trained with each frame independently. Code is available at: https://tinyurl.com/segment-video

Yifan Liu, Changyong Shun, Jingdong Wang et al.

In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly borrow the distillation scheme for image classification and perform knowledge distillation for each pixel separately, leading to sub-optimal performance. Here we propose to distill structured knowledge from large networks to compact networks, taking into account the fact that dense prediction is a structured prediction problem. Specifically, we study two structured distillation schemes: i) pair-wise distillation that distills the pair-wise similarities by building a static graph; and ii) holistic distillation that uses adversarial training to distill holistic knowledge. The effectiveness of our knowledge distillation approaches is demonstrated by experiments on three dense prediction tasks: semantic segmentation, depth estimation and object detection. Code is available at: https://git.io/StructKD

Liang Xu, Xintao Lv, Yichao Yan et al.

The analysis of the ubiquitous human-human interactions is pivotal for understanding humans as social beings. Existing human-human interaction datasets typically suffer from inaccurate body motions, lack of hand gestures and fine-grained textual descriptions. To better perceive and generate human-human interactions, we propose Inter-X, a currently largest human-human interaction dataset with accurate body movements and diverse interaction patterns, together with detailed hand gestures. The dataset includes ~11K interaction sequences and more than 8.1M frames. We also equip Inter-X with versatile annotations of more than 34K fine-grained human part-level textual descriptions, semantic interaction categories, interaction order, and the relationship and personality of the subjects. Based on the elaborate annotations, we propose a unified benchmark composed of 4 categories of downstream tasks from both the perceptual and generative directions. Extensive experiments and comprehensive analysis show that Inter-X serves as a testbed for promoting the development of versatile human-human interaction analysis. Our dataset and benchmark will be publicly available for research purposes.

Chenxin Li, Hengyu Liu, Yifan Liu et al.

Generative models hold promise for revolutionizing medical education, robot-assisted surgery, and data augmentation for machine learning. Despite progress in generating 2D medical images, the complex domain of clinical video generation has largely remained untapped.This paper introduces \model, an innovative approach to generate medical videos that simulate clinical endoscopy scenes. We present a novel generative model design that integrates a meticulously crafted spatial-temporal video transformer with advanced 2D vision foundation model priors, explicitly modeling spatial-temporal dynamics during video generation. We also pioneer the first public benchmark for endoscopy simulation with video generation models, adapting existing state-of-the-art methods for this endeavor.Endora demonstrates exceptional visual quality in generating endoscopy videos, surpassing state-of-the-art methods in extensive testing. Moreover, we explore how this endoscopy simulator can empower downstream video analysis tasks and even generate 3D medical scenes with multi-view consistency. In a nutshell, Endora marks a notable breakthrough in the deployment of generative AI for clinical endoscopy research, setting a substantial stage for further advances in medical content generation. For more details, please visit our project page: https://endora-medvidgen.github.io/.

Jiancheng Huang, Yi Huang, Jianzhuang Liu et al.

Text-conditional image editing is a practical AIGC task that has recently emerged with great commercial and academic value. For real image editing, most diffusion model-based methods use DDIM Inversion as the first stage before editing. However, DDIM Inversion often results in reconstruction failure, leading to unsatisfactory performance for downstream editing. To address this problem, we first analyze why the reconstruction via DDIM Inversion fails. We then propose a new inversion and sampling method named Dual-Schedule Inversion. We also design a classifier to adaptively combine Dual-Schedule Inversion with different editing methods for user-friendly image editing. Our work can achieve superior reconstruction and editing performance with the following advantages: 1) It can reconstruct real images perfectly without fine-tuning, and its reversibility is guaranteed mathematically. 2) The edited object/scene conforms to the semantics of the text prompt. 3) The unedited parts of the object/scene retain the original identity.

Yifan Liu, Jiancheng Huang, Na Liu et al.

Document shadows are a major obstacle in the digitization process. Due to the dense information in text and patterns covered by shadows, document shadow removal requires specialized methods. Existing document shadow removal methods, although showing some progress, still rely on additional information such as shadow masks or lack generalization and effectiveness across different shadow scenarios. This often results in incomplete shadow removal or loss of original document content and tones. Moreover, these methods tend to underutilize the information present in the original shadowed document image. In this paper, we refocus our approach on the document images themselves, which inherently contain rich information.We propose an end-to-end document shadow removal method guided by contrast representation, following a coarse-to-fine refinement approach. By extracting document contrast information, we can effectively and quickly locate shadow shapes and positions without the need for additional masks. This information is then integrated into the refined shadow removal process, providing better guidance for network-based removal and feature fusion. Extensive qualitative and quantitative experiments show that our method achieves state-of-the-art performance.

Yipeng Zhang, Yifan Liu, Zonghao Guo et al.

Vision transformers (ViTs) are widely employed in multimodal large language models (MLLMs) for visual encoding. However, they exhibit inferior performance on tasks regarding fine-grained visual perception. We attribute this to the limitations of ViTs in capturing diverse multi-modal visual levels, such as low-level details. To address this issue, we present LLaVA-UHD v2, an MLLM with advanced perception abilities by introducing a well-designed vision-language projector, the Hierarchical window (Hiwin) transformer. Hiwin transformer enhances MLLM's ability to capture diverse multi-modal visual granularities, by incorporating our constructed high-resolution semantic pyramid. Specifically, Hiwin transformer comprises two key modules: (i) a visual detail injection module, which progressively injects low-level visual details into high-level language-aligned semantics features, thereby forming an inverse semantic pyramid (ISP), and (ii) a hierarchical window attention module, which leverages cross-scale windows to condense multi-level semantics from the ISP. Extensive experiments show that LLaVA-UHD v2 outperforms compared MLLMs on a wide range of benchmarks. Notably, our design achieves an average boost of 3.7% across 14 benchmarks compared with the baseline method, 9.3% on DocVQA for instance. All the data and code will be publicly available to facilitate future research.

Xuqian Ren, Yifan Liu, Chunlei Song

Image matting and image harmonization are two important tasks in image composition. Image matting, aiming to achieve foreground boundary details, and image harmonization, aiming to make the background compatible with the foreground, are both promising yet challenging tasks. Previous works consider optimizing these two tasks separately, which may lead to a sub-optimal solution. We propose to optimize matting and harmonization simultaneously to get better performance on both the two tasks and achieve more natural results. We propose a new Generative Adversarial (GAN) framework which optimizing the matting network and the harmonization network based on a self-attention discriminator. The discriminator is required to distinguish the natural images from different types of fake synthesis images. Extensive experiments on our constructed dataset demonstrate the effectiveness of our proposed method. Our dataset and dataset generating pipeline can be found in \url{https://git.io/HaMaGAN}

Bowen Zhang, Yifan Liu, Zhi Tian et al.

Semantic segmentation requires per-pixel prediction for a given image. Typically, the output resolution of a segmentation network is severely reduced due to the downsampling operations in the CNN backbone. Most previous methods employ upsampling decoders to recover the spatial resolution. Various decoders were designed in the literature. Here, we propose a novel decoder, termed dynamic neural representational decoder (NRD), which is simple yet significantly more efficient. As each location on the encoder's output corresponds to a local patch of the semantic labels, in this work, we represent these local patches of labels with compact neural networks. This neural representation enables our decoder to leverage the smoothness prior in the semantic label space, and thus makes our decoder more efficient. Furthermore, these neural representations are dynamically generated and conditioned on the outputs of the encoder networks. The desired semantic labels can be efficiently decoded from the neural representations, resulting in high-resolution semantic segmentation predictions. We empirically show that our proposed decoder can outperform the decoder in DeeplabV3+ with only 30% computational complexity, and achieve competitive performance with the methods using dilated encoders with only 15% computation. Experiments on the Cityscapes, ADE20K, and PASCAL Context datasets demonstrate the effectiveness and efficiency of our proposed method.

Jianlong Yuan, Yifan Liu, Chunhua Shen et al.

Recently, significant progress has been made on semantic segmentation. However, the success of supervised semantic segmentation typically relies on a large amount of labelled data, which is time-consuming and costly to obtain. Inspired by the success of semi-supervised learning methods in image classification, here we propose a simple yet effective semi-supervised learning framework for semantic segmentation. We demonstrate that the devil is in the details: a set of simple design and training techniques can collectively improve the performance of semi-supervised semantic segmentation significantly. Previous works [3, 27] fail to employ strong augmentation in pseudo label learning efficiently, as the large distribution change caused by strong augmentation harms the batch normalisation statistics. We design a new batch normalisation, namely distribution-specific batch normalisation (DSBN) to address this problem and demonstrate the importance of strong augmentation for semantic segmentation. Moreover, we design a self correction loss which is effective in noise resistance. We conduct a series of ablation studies to show the effectiveness of each component. Our method achieves state-of-the-art results in the semi-supervised settings on the Cityscapes and Pascal VOC datasets.

Yifan Liu, Hao Chen, Yu Chen et al.

The perceptual loss has been widely used as an effective loss term in image synthesis tasks including image super-resolution, and style transfer. It was believed that the success lies in the high-level perceptual feature representations extracted from CNNs pretrained with a large set of images. Here we reveal that, what matters is the network structure instead of the trained weights. Without any learning, the structure of a deep network is sufficient to capture the dependencies between multiple levels of variable statistics using multiple layers of CNNs. This insight removes the requirements of pre-training and a particular network structure (commonly, VGG) that are previously assumed for the perceptual loss, thus enabling a significantly wider range of applications. To this end, we demonstrate that a randomly-weighted deep CNN can be used to model the structured dependencies of outputs. On a few dense per-pixel prediction tasks such as semantic segmentation, depth estimation and instance segmentation, we show improved results of using the extended randomized perceptual loss, compared to the baselines using pixel-wise loss alone. We hope that this simple, extended perceptual loss may serve as a generic structured-output loss that is applicable to most structured output learning tasks.

He Zhang, Zhixiong Nan, Tao Yang et al.

In autonomous driving, perceiving the driving behaviors of surrounding agents is important for the ego-vehicle to make a reasonable decision. In this paper, we propose a neural network model based on trajectories information for driving behavior recognition. Unlike existing trajectory-based methods that recognize the driving behavior using the hand-crafted features or directly encoding the trajectory, our model involves a Multi-Scale Convolutional Neural Network (MSCNN) module to automatically extract the high-level features which are supposed to encode the rich spatial and temporal information. Given a trajectory sequence of an agent as the input, firstly, the Bi-directional Long Short Term Memory (Bi-LSTM) module and the MSCNN module respectively process the input, generating two features, and then the two features are fused to classify the behavior of the agent. We evaluate the proposed model on the public BLVD dataset, achieving a satisfying performance.

Zhikang Zou, Yifan Liu, Shuangjie Xu et al.

The task of crowd counting is extremely challenging due to complicated difficulties, especially the huge variation in vision scale. Previous works tend to adopt a naive concatenation of multi-scale information to tackle it, while the scale shifts between the feature maps are ignored. In this paper, we propose a novel Hierarchical Scale Recalibration Network (HSRNet), which addresses the above issues by modeling rich contextual dependencies and recalibrating multiple scale-associated information. Specifically, a Scale Focus Module (SFM) first integrates global context into local features by modeling the semantic inter-dependencies along channel and spatial dimensions sequentially. In order to reallocate channel-wise feature responses, a Scale Recalibration Module (SRM) adopts a step-by-step fusion to generate final density maps. Furthermore, we propose a novel Scale Consistency loss to constrain that the scale-associated outputs are coherent with groundtruth of different scales. With the proposed modules, our approach can ignore various noises selectively and focus on appropriate crowd scales automatically. Extensive experiments on crowd counting datasets (ShanghaiTech, MALL, WorldEXPO'10, and UCSD) show that our HSRNet can deliver superior results over all state-of-the-art approaches. More remarkably, we extend experiments on an extra vehicle dataset, whose results indicate that the proposed model is generalized to other applications.

Wei Yin, Xinlong Wang, Chunhua Shen et al.

We present a method for depth estimation with monocular images, which can predict high-quality depth on diverse scenes up to an affine transformation, thus preserving accurate shapes of a scene. Previous methods that predict metric depth often work well only for a specific scene. In contrast, learning relative depth (information of being closer or further) can enjoy better generalization, with the price of failing to recover the accurate geometric shape of the scene. In this work, we propose a dataset and methods to tackle this dilemma, aiming to predict accurate depth up to an affine transformation with good generalization to diverse scenes. First we construct a large-scale and diverse dataset, termed Diverse Scene Depth dataset (DiverseDepth), which has a broad range of scenes and foreground contents. Compared with previous learning objectives, i.e., learning metric depth or relative depth, we propose to learn the affine-invariant depth using our diverse dataset to ensure both generalization and high-quality geometric shapes of scenes. Furthermore, in order to train the model on the complex dataset effectively, we propose a multi-curriculum learning method. Experiments show that our method outperforms previous methods on 8 datasets by a large margin with the zero-shot test setting, demonstrating the excellent generalization capacity of the learned model to diverse scenes. The reconstructed point clouds with the predicted depth show that our method can recover high-quality 3D shapes. Code and dataset are available at: https://tinyurl.com/DiverseDepth

Yifan Liu, Bohan Zhuang, Chunhua Shen et al.

Multi-task learning (MTL) is an efficient solution to solve multiple tasks simultaneously in order to get better speed and performance than handling each single-task in turn. The most current methods can be categorized as either: (i) hard parameter sharing where a subset of the parameters is shared among tasks while other parameters are task-specific; or (ii) soft parameter sharing where all parameters are task-specific but they are jointly regularized. Both methods suffer from limitations: the shared hidden layers of the former are difficult to optimize due to the competing objectives while the complexity of the latter grows linearly with the increasing number of tasks. To mitigate those drawbacks, this paper proposes an alternative, where we explicitly construct an auxiliary module to mimic the soft parameter sharing for assisting the optimization of the hard parameter sharing layers in the training phase. In particular, the auxiliary module takes the outputs of the shared hidden layers as inputs and is supervised by the auxiliary task loss. During training, the auxiliary module is jointly optimized with the MTL network, serving as a regularization by introducing an inductive bias to the shared layers. In the testing phase, only the original MTL network is kept. Thus our method avoids the limitation of both categories. We evaluate the proposed auxiliary module on pixel-wise prediction tasks, including semantic segmentation, depth estimation, and surface normal prediction with different network structures. The extensive experiments over various settings verify the effectiveness of our methods.

Yang Zhao, Yifan Liu, Chunhua Shen et al.

Facial landmark detection is a crucial prerequisite for many face analysis applications. Deep learning-based methods currently dominate the approach of addressing the facial landmark detection. However, such works generally introduce a large number of parameters, resulting in high memory cost. In this paper, we aim for a lightweight as well as effective solution to facial landmark detection. To this end, we propose an effective lightweight model, namely Mobile Face Alignment Network (MobileFAN), using a simple backbone MobileNetV2 as the encoder and three deconvolutional layers as the decoder. The proposed MobileFAN, with only 8% of the model size and lower computational cost, achieves superior or equivalent performance compared with state-of-the-art models. Moreover, by transferring the geometric structural information of a face graph from a large complex model to our proposed MobileFAN through feature-aligned distillation and feature-similarity distillation, the performance of MobileFAN is further improved in effectiveness and efficiency for face alignment. Extensive experiment results on three challenging facial landmark estimation benchmarks including COFW, 300W and WFLW show the superiority of our proposed MobileFAN against state-of-the-art methods.

Wei Yin, Yifan Liu, Chunhua Shen et al.

Monocular depth prediction plays a crucial role in understanding 3D scene geometry. Although recent methods have achieved impressive progress in evaluation metrics such as the pixel-wise relative error, most methods neglect the geometric constraints in the 3D space. In this work, we show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces one simple type of geometric constraints, namely, virtual normal directions determined by randomly sampled three points in the reconstructed 3D space, we can considerably improve the depth prediction accuracy. Significantly, the byproduct of this predicted depth being sufficiently accurate is that we are now able to recover good 3D structures of the scene such as the point cloud and surface normal directly from the depth, eliminating the necessity of training new sub-models as was previously done. Experiments on two benchmarks: NYU Depth-V2 and KITTI demonstrate the effectiveness of our method and state-of-the-art performance.

Shuangting Liu, Jiaqi Zhang, Yuxin Chen et al.

Semantic segmentation is one of the basic topics in computer vision, it aims to assign semantic labels to every pixel of an image. Unbalanced semantic label distribution could have a negative influence on segmentation accuracy. In this paper, we investigate using data augmentation approach to balance the semantic label distribution in order to improve segmentation performance. We propose using generative adversarial networks (GANs) to generate realistic images for improving the performance of semantic segmentation networks. Experimental results show that the proposed method can not only improve segmentation performance on those classes with low accuracy, but also obtain 1.3% to 2.1% increase in average segmentation accuracy. It shows that this augmentation method can boost accuracy and be easily applicable to any other segmentation models.

Xinyue Zhu, Yifan Liu, Zengchang Qin et al.

It is a difficult task to classify images with multiple class labels using only a small number of labeled examples, especially when the label (class) distribution is imbalanced. Emotion classification is such an example of imbalanced label distribution, because some classes of emotions like \emph{disgusted} are relatively rare comparing to other labels like {\it happy or sad}. In this paper, we propose a data augmentation method using generative adversarial networks (GAN). It can complement and complete the data manifold and find better margins between neighboring classes. Specifically, we design a framework with a CNN model as the classifier and a cycle-consistent adversarial networks (CycleGAN) as the generator. In order to avoid gradient vanishing problem, we employ the least-squared loss as adversarial loss. We also propose several evaluation methods on three benchmark datasets to validate GAN's performance. Empirical results show that we can obtain 5%~10% increase in the classification accuracy after employing the GAN-based data augmentation techniques.

Yifan Liu, Zengchang Qin, Zhenbo Luo et al.

Recently, realistic image generation using deep neural networks has become a hot topic in machine learning and computer vision. Images can be generated at the pixel level by learning from a large collection of images. Learning to generate colorful cartoon images from black-and-white sketches is not only an interesting research problem, but also a potential application in digital entertainment. In this paper, we investigate the sketch-to-image synthesis problem by using conditional generative adversarial networks (cGAN). We propose the auto-painter model which can automatically generate compatible colors for a sketch. The new model is not only capable of painting hand-draw sketch with proper colors, but also allowing users to indicate preferred colors. Experimental results on two sketch datasets show that the auto-painter performs better that existing image-to-image methods.