Chi Zhang

Wei Yin, Chi Zhang, Hao Chen et al. · tencent-ai

Reconstructing accurate 3D scenes from images is a long-standing vision task. Due to the ill-posedness of the single-image reconstruction problem, most well-established methods are built upon multi-view geometry. State-of-the-art (SOTA) monocular metric depth estimation methods can only handle a single camera model and are unable to perform mixed-data training due to the metric ambiguity. Meanwhile, SOTA monocular methods trained on large mixed datasets achieve zero-shot generalization by learning affine-invariant depths, which cannot recover real-world metrics. In this work, we show that the key to a zero-shot single-view metric depth model lies in the combination of large-scale data training and resolving the metric ambiguity from various camera models. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problems and can be effortlessly plugged into existing monocular models. Equipped with our module, monocular models can be stably trained with over 8 million images with thousands of camera models, resulting in zero-shot generalization to in-the-wild images with unseen camera settings. Experiments demonstrate SOTA performance of our method on 7 zero-shot benchmarks. Notably, our method won the championship in the 2nd Monocular Depth Estimation Challenge. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images, paving the way for plausible single-image metrology. The potential benefits extend to downstream tasks, which can be significantly improved by simply plugging in our model. For example, our model relieves the scale drift issues of monocular-SLAM (Fig. 1), leading to high-quality metric scale dense mapping. The code is available at https://github.com/YvanYin/Metric3D.

Yuqing Wen, Yucheng Zhao, Yingfei Liu et al.

The field of autonomous driving increasingly demands high-quality annotated training data. In this paper, we propose Panacea, an innovative approach to generate panoramic and controllable videos in driving scenarios, capable of yielding an unlimited numbers of diverse, annotated samples pivotal for autonomous driving advancements. Panacea addresses two critical challenges: 'Consistency' and 'Controllability.' Consistency ensures temporal and cross-view coherence, while Controllability ensures the alignment of generated content with corresponding annotations. Our approach integrates a novel 4D attention and a two-stage generation pipeline to maintain coherence, supplemented by the ControlNet framework for meticulous control by the Bird's-Eye-View (BEV) layouts. Extensive qualitative and quantitative evaluations of Panacea on the nuScenes dataset prove its effectiveness in generating high-quality multi-view driving-scene videos. This work notably propels the field of autonomous driving by effectively augmenting the training dataset used for advanced BEV perception techniques.

Limeng Qiao, Yongchao Zheng, Peng Zhang et al.

This report introduces the 1st place winning solution for the Autonomous Driving Challenge 2023 - Online HD-map Construction. By delving into the vectorization pipeline, we elaborate an effective architecture, termed as MachMap, which formulates the task of HD-map construction as the point detection paradigm in the bird-eye-view space with an end-to-end manner. Firstly, we introduce a novel map-compaction scheme into our framework, leading to reducing the number of vectorized points by 93% without any expression performance degradation. Build upon the above process, we then follow the general query-based paradigm and propose a strong baseline with integrating a powerful CNN-based backbone like InternImage, a temporal-based instance decoder and a well-designed point-mask coupling head. Additionally, an extra optional ensemble stage is utilized to refine model predictions for better performance. Our MachMap-tiny with IN-1K initialization achieves a mAP of 79.1 on the Argoverse2 benchmark and the further improved MachMap-huge reaches the best mAP of 83.5, outperforming all the other online HD-map construction approaches on the final leaderboard with a distinct performance margin (> 9.8 mAP at least).

Limeng Qiao, Wenjie Ding, Xi Qiu et al.

Vectorized high-definition map (HD-map) construction, which focuses on the perception of centimeter-level environmental information, has attracted significant research interest in the autonomous driving community. Most existing approaches first obtain rasterized map with the segmentation-based pipeline and then conduct heavy post-processing for downstream-friendly vectorization. In this paper, by delving into parameterization-based methods, we pioneer a concise and elegant scheme that adopts unified piecewise Bezier curve. In order to vectorize changeful map elements end-to-end, we elaborate a simple yet effective architecture, named Piecewise Bezier HD-map Network (BeMapNet), which is formulated as a direct set prediction paradigm and postprocessing-free. Concretely, we first introduce a novel IPM-PE Align module to inject 3D geometry prior into BEV features through common position encoding in Transformer. Then a well-designed Piecewise Bezier Head is proposed to output the details of each map element, including the coordinate of control points and the segment number of curves. In addition, based on the progressively restoration of Bezier curve, we also present an efficient Point-Curve-Region Loss for supervising more robust and precise HD-map modeling. Extensive comparisons show that our method is remarkably superior to other existing SOTAs by 18.0 mAP at least.

Guangyuan Jiang, Manjie Xu, Shiji Xin et al.

Without explicit feedback, humans can rapidly learn the meaning of words. Children can acquire a new word after just a few passive exposures, a process known as fast mapping. This word learning capability is believed to be the most fundamental building block of multimodal understanding and reasoning. Despite recent advancements in multimodal learning, a systematic and rigorous evaluation is still missing for human-like word learning in machines. To fill in this gap, we introduce the MachinE Word Learning (MEWL) benchmark to assess how machines learn word meaning in grounded visual scenes. MEWL covers human's core cognitive toolkits in word learning: cross-situational reasoning, bootstrapping, and pragmatic learning. Specifically, MEWL is a few-shot benchmark suite consisting of nine tasks for probing various word learning capabilities. These tasks are carefully designed to be aligned with the children's core abilities in word learning and echo the theories in the developmental literature. By evaluating multimodal and unimodal agents' performance with a comparative analysis of human performance, we notice a sharp divergence in human and machine word learning. We further discuss these differences between humans and machines and call for human-like few-shot word learning in machines.

Ruibo Li, Chi Zhang, Zhe Wang et al.

In this article, we investigate self-supervised 3D scene flow estimation and class-agnostic motion prediction on point clouds. A realistic scene can be well modeled as a collection of rigidly moving parts, therefore its scene flow can be represented as a combination of the rigid motion of these individual parts. Building upon this observation, we propose to generate pseudo scene flow labels for self-supervised learning through piecewise rigid motion estimation, in which the source point cloud is decomposed into local regions and each region is treated as rigid. By rigidly aligning each region with its potential counterpart in the target point cloud, we obtain a region-specific rigid transformation to generate its pseudo flow labels. To mitigate the impact of potential outliers on label generation, when solving the rigid registration for each region, we alternately perform three steps: establishing point correspondences, measuring the confidence for the correspondences, and updating the rigid transformation based on the correspondences and their confidence. As a result, confident correspondences will dominate label generation and a validity mask will be derived for the generated pseudo labels. By using the pseudo labels together with their validity mask for supervision, models can be trained in a self-supervised manner. Extensive experiments on FlyingThings3D and KITTI datasets demonstrate that our method achieves new state-of-the-art performance in self-supervised scene flow learning, without any ground truth scene flow for supervision, even performing better than some supervised counterparts. Additionally, our method is further extended to class-agnostic motion prediction and significantly outperforms previous state-of-the-art self-supervised methods on nuScenes dataset.

Binxin Yang, Xuejin Chen, Chaoqun Wang et al.

With recent advances in image-to-image translation tasks, remarkable progress has been witnessed in generating face images from sketches. However, existing methods frequently fail to generate images with details that are semantically and geometrically consistent with the input sketch, especially when various decoration strokes are drawn. To address this issue, we introduce a novel W-W+ encoder architecture to take advantage of the high expressive power of W+ space and semantic controllability of W space. We introduce an explicit intermediate representation for sketch semantic embedding. With a semantic feature matching loss for effective semantic supervision, our sketch embedding precisely conveys the semantics in the input sketches to the synthesized images. Moreover, a novel sketch semantic interpretation approach is designed to automatically extract semantics from vectorized sketches. We conduct extensive experiments on both synthesized sketches and hand-drawn sketches, and the results demonstrate the superiority of our method over existing approaches on both semantics-preserving and generalization ability.

Yuqing Wen, Yucheng Zhao, Yingfei Liu et al.

The field of autonomous driving increasingly demands high-quality annotated video training data. In this paper, we propose Panacea+, a powerful and universally applicable framework for generating video data in driving scenes. Built upon the foundation of our previous work, Panacea, Panacea+ adopts a multi-view appearance noise prior mechanism and a super-resolution module for enhanced consistency and increased resolution. Extensive experiments show that the generated video samples from Panacea+ greatly benefit a wide range of tasks on different datasets, including 3D object tracking, 3D object detection, and lane detection tasks on the nuScenes and Argoverse 2 dataset. These results strongly prove Panacea+ to be a valuable data generation framework for autonomous driving.

Jiang-Xin Shi, Chi Zhang, Tong Wei et al.

Pre-trained vision-language models like CLIP have shown powerful zero-shot inference ability via image-text matching and prove to be strong few-shot learners in various downstream tasks. However, in real-world scenarios, adapting CLIP to downstream tasks may encounter the following challenges: 1) data may exhibit long-tailed data distributions and might not have abundant samples for all the classes; 2) There might be emerging tasks with new classes that contain no samples at all. To overcome them, we propose a novel framework to achieve efficient and long-tailed generalization, which can be termed as Candle. During the training process, we propose compensating logit-adjusted loss to encourage large margins of prototypes and alleviate imbalance both within the base classes and between the base and new classes. For efficient adaptation, we treat the CLIP model as a black box and leverage the extracted features to obtain visual and textual prototypes for prediction. To make full use of multi-modal information, we also propose cross-modal attention to enrich the features from both modalities. For effective generalization, we introduce virtual prototypes for new classes to make up for their lack of training images. Candle achieves state-of-the-art performance over extensive experiments on 11 diverse datasets while substantially reducing the training time, demonstrating the superiority of our approach. The source code is available at https://github.com/shijxcs/Candle.

Yuxuan Yan, Chi Zhang, Rui Wang et al.

This study investigates identity-preserving image synthesis, an intriguing task in image generation that seeks to maintain a subject's identity while adding a personalized, stylistic touch. Traditional methods, such as Textual Inversion and DreamBooth, have made strides in custom image creation, but they come with significant drawbacks. These include the need for extensive resources and time for fine-tuning, as well as the requirement for multiple reference images. To overcome these challenges, our research introduces a novel approach to identity-preserving synthesis, with a particular focus on human images. Our model leverages a direct feed-forward mechanism, circumventing the need for intensive fine-tuning, thereby facilitating quick and efficient image generation. Central to our innovation is a hybrid guidance framework, which combines stylized images, facial images, and textual prompts to guide the image generation process. This unique combination enables our model to produce a variety of applications, such as artistic portraits and identity-blended images. Our experimental results, including both qualitative and quantitative evaluations, demonstrate the superiority of our method over existing baseline models and previous works, particularly in its remarkable efficiency and ability to preserve the subject's identity with high fidelity.

Zhende Song, Chenchen Wang, Jiamu Sheng et al.

Recent large vision-language models (LVLMs) for video understanding are primarily fine-tuned with various videos scraped from online platforms. Existing datasets, such as ActivityNet, require considerable human labor for structuring and annotation before effectively utilized for tuning LVLMs. While current LVLMs are primarily trained on existing datasets in broad, general-purpose settings, adapting them to specific downstream scenarios remains challenging, as collecting and annotating task-specific videos is highly labor-intensive and time-consuming. To address this issue, we propose a three-stage framework named DreamFrame for automatically generating style-consistent keyframes and corresponding question-answer (QA) pairs to support LVLM instruction tuning. DreamFrame generates datasets in a movie-like manner. First, we utilize an LLM to generate structured movie plots including movie prior information (like overview and style), frame descriptions and plot-related QA pairs, with a story expansion strategy to mitigate context length limitations.Then, to ensure visual consistency across generated frames, we design a Style Immobilization Process which maintains consistent style through an embedding learning strategy. Finally, frame descriptions and style embeddings are integrated to produce coherent keyframes. Using DreamFrame, we construct a dataset comprising approximately 1k stylized keyframe-like videos and 100k diverse QA pairs. Extensive fine-tuned experiments on various LVLM architectures demonstrate the effectiveness of the proposed dataset. Furthermore, based on the proposed dataset, we fine-tune a new LVLM named DreamFrame-7B, which significantly surpasses the previous similar-sized LVLMs across different benchmarks.

Chen Wei, Chi Zhang, Jiachen Zou et al.

Human decision-making in cognitive tasks and daily life exhibits considerable variability, shaped by factors such as task difficulty, individual preferences, and personal experiences. Understanding this variability across individuals is essential for uncovering the perceptual and decision-making mechanisms that humans rely on when faced with uncertainty and ambiguity. We present a computational framework BAM (Boundary Alignment & Manipulation framework) that combines perceptual boundary sampling in ANNs and human behavioral experiments to systematically investigate this phenomenon. Our perceptual boundary sampling algorithm generates stimuli along ANN decision boundaries that intrinsically induce significant perceptual variability. The efficacy of these stimuli is empirically validated through large-scale behavioral experiments involving 246 participants across 116,715 trials, culminating in the variMNIST dataset containing 19,943 systematically annotated images. Through personalized model alignment and adversarial generation, we establish a reliable method for simultaneously predicting and manipulating the divergent perceptual decisions of pairs of participants. This work bridges the gap between computational models and human individual difference research, providing new tools for personalized perception analysis.

Haotian Deng, Chi Zhang, Chen Wei et al.

A fundamental challenge in affective cognitive science is to develop models that accurately capture the relationship between external emotional stimuli and human internal experiences. While ANNs have demonstrated remarkable accuracy in facial expression recognition, their ability to model inter-individual differences in human perception remains underexplored. This study investigates the phenomenon of high perceptual variability-where individuals exhibit significant differences in emotion categorization even when viewing the same stimulus. Inspired by the similarity between ANNs and human perception, we hypothesize that facial expression samples that are ambiguous for ANN classifiers also elicit divergent perceptual judgments among human observers. To examine this hypothesis, we introduce a novel perceptual boundary sampling method to generate facial expression stimuli that lie along ANN decision boundaries. These ambiguous samples form the basis of the varEmotion dataset, constructed through large-scale human behavioral experiments. Our analysis reveals that these ANN-confusing stimuli also provoke heightened perceptual uncertainty in human participants, highlighting shared computational principles in emotion perception. Finally, by fine-tuning ANN representations using behavioral data, we achieve alignment between ANN predictions and both group-level and individual-level human perceptual patterns. Our findings establish a systematic link between ANN decision boundaries and human perceptual variability, offering new insights into personalized modeling of emotional interpretation.

Xiaolin Yan, Yangxing Liu, Jiazhang Zheng et al.

Large language models (LLMs) have recently achieved significant advances in reasoning and demonstrated their advantages in solving challenging problems. Yet, their effectiveness in the semiconductor display industry remains limited due to a lack of domain-specific training and expertise. To bridge this gap, we present X-Intelligence 3.0, the first high-performance reasoning model specifically developed for the semiconductor display industry. This model is designed to deliver expert-level understanding and reasoning for the industry's complex challenges. Leveraging a carefully curated industry knowledge base, the model undergoes supervised fine-tuning and reinforcement learning to enhance its reasoning and comprehension capabilities. To further accelerate development, we implemented an automated evaluation framework that simulates expert-level assessments. We also integrated a domain-specific retrieval-augmented generation (RAG) mechanism, resulting in notable performance gains on benchmark datasets. Despite its relatively compact size of 32 billion parameters, X-Intelligence 3.0 outperforms SOTA DeepSeek-R1-671B across multiple evaluations. This demonstrates its exceptional efficiency and establishes it as a powerful solution to the longstanding reasoning challenges faced by the semiconductor display industry.

Chi Zhang, Yiwen Chen, Yijun Fu et al.

The recent advancements in image-text diffusion models have stimulated research interest in large-scale 3D generative models. Nevertheless, the limited availability of diverse 3D resources presents significant challenges to learning. In this paper, we present a novel method for generating high-quality, stylized 3D avatars that utilizes pre-trained image-text diffusion models for data generation and a Generative Adversarial Network (GAN)-based 3D generation network for training. Our method leverages the comprehensive priors of appearance and geometry offered by image-text diffusion models to generate multi-view images of avatars in various styles. During data generation, we employ poses extracted from existing 3D models to guide the generation of multi-view images. To address the misalignment between poses and images in data, we investigate view-specific prompts and develop a coarse-to-fine discriminator for GAN training. We also delve into attribute-related prompts to increase the diversity of the generated avatars. Additionally, we develop a latent diffusion model within the style space of StyleGAN to enable the generation of avatars based on image inputs. Our approach demonstrates superior performance over current state-of-the-art methods in terms of visual quality and diversity of the produced avatars.

Zhuyu Yao, Jiangbo Ai, Boxun Li et al.

The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively, without which their performance degrades seriously. In this paper, we investigate that the random initialization of object containers, which include object queries and reference points, is mainly responsible for the requirement of multiple iterations. Based on our findings, we propose Efficient DETR, a simple and efficient pipeline for end-to-end object detection. By taking advantage of both dense detection and sparse set detection, Efficient DETR leverages dense prior to initialize the object containers and brings the gap of the 1-decoder structure and 6-decoder structure. Experiments conducted on MS COCO show that our method, with only 3 encoder layers and 1 decoder layer, achieves competitive performance with state-of-the-art object detection methods. Efficient DETR is also robust in crowded scenes. It outperforms modern detectors on CrowdHuman dataset by a large margin.

Yifan Sun, Changmao Cheng, Yuhan Zhang et al.

This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity $s_p$ and minimize the between-class similarity $s_n$. We find a majority of loss functions, including the triplet loss and the softmax plus cross-entropy loss, embed $s_n$ and $s_p$ into similarity pairs and seek to reduce $(s_n-s_p)$. Such an optimization manner is inflexible, because the penalty strength on every single similarity score is restricted to be equal. Our intuition is that if a similarity score deviates far from the optimum, it should be emphasized. To this end, we simply re-weight each similarity to highlight the less-optimized similarity scores. It results in a Circle loss, which is named due to its circular decision boundary. The Circle loss has a unified formula for two elemental deep feature learning approaches, i.e. learning with class-level labels and pair-wise labels. Analytically, we show that the Circle loss offers a more flexible optimization approach towards a more definite convergence target, compared with the loss functions optimizing $(s_n-s_p)$. Experimentally, we demonstrate the superiority of the Circle loss on a variety of deep feature learning tasks. On face recognition, person re-identification, as well as several fine-grained image retrieval datasets, the achieved performance is on par with the state of the art.

Chenyou Fan, Xiaofan Zhang, Shu Zhang et al.

In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion features; 2) a redesigned question memory which helps understand the complex semantics of question and highlights queried subjects; and 3) a new multimodal fusion layer which performs multi-step reasoning by attending to relevant visual and textual hints with self-updated attention. Our VideoQA model firstly generates the global context-aware visual and textual features respectively by interacting current inputs with memory contents. After that, it makes the attentional fusion of the multimodal visual and textual representations to infer the correct answer. Multiple cycles of reasoning can be made to iteratively refine attention weights of the multimodal data and improve the final representation of the QA pair. Experimental results demonstrate our approach achieves state-of-the-art performance on four VideoQA benchmark datasets.

Chi Zhang, Feng Gao, Baoxiong Jia et al.

Dramatic progress has been witnessed in basic vision tasks involving low-level perception, such as object recognition, detection, and tracking. Unfortunately, there is still an enormous performance gap between artificial vision systems and human intelligence in terms of higher-level vision problems, especially ones involving reasoning. Earlier attempts in equipping machines with high-level reasoning have hovered around Visual Question Answering (VQA), one typical task associating vision and language understanding. In this work, we propose a new dataset, built in the context of Raven's Progressive Matrices (RPM) and aimed at lifting machine intelligence by associating vision with structural, relational, and analogical reasoning in a hierarchical representation. Unlike previous works in measuring abstract reasoning using RPM, we establish a semantic link between vision and reasoning by providing structure representation. This addition enables a new type of abstract reasoning by jointly operating on the structure representation. Machine reasoning ability using modern computer vision is evaluated in this newly proposed dataset. Additionally, we also provide human performance as a reference. Finally, we show consistent improvement across all models by incorporating a simple neural module that combines visual understanding and structure reasoning.

Nevrez Imamoglu, Chi Zhang, Wataru Shimoda et al.

As prior knowledge of objects or object features helps us make relations for similar objects on attentional tasks, pre-trained deep convolutional neural networks (CNNs) can be used to detect salient objects on images regardless of the object class is in the network knowledge or not. In this paper, we propose a top-down saliency model using CNN, a weakly supervised CNN model trained for 1000 object labelling task from RGB images. The model detects attentive regions based on their objectness scores predicted by selected features from CNNs. To estimate the salient objects effectively, we combine both forward and backward features, while demonstrating that partially-guided backpropagation will provide sufficient information for selecting the features from forward run of CNN model. Finally, these top-down cues are enhanced with a state-of-the-art bottom-up model as complementing the overall saliency. As the proposed model is an effective integration of forward and backward cues through objectness without any supervision or regression to ground truth data, it gives promising results compared to state-of-the-art models in two different datasets.

Zhen Dong, Su Jia, Chi Zhang et al.

Recently, deep neural network has shown promising performance in face image recognition. The inputs of most networks are face images, and there is hardly any work reported in literature on network with face videos as input. To sufficiently discover the useful information contained in face videos, we present a novel network architecture called input aggregated network which is able to learn fixed-length representations for variable-length face videos. To accomplish this goal, an aggregation unit is designed to model a face video with various frames as a point on a Riemannian manifold, and the mapping unit aims at mapping the point into high-dimensional space where face videos belonging to the same subject are close-by and others are distant. These two units together with the frame representation unit build an end-to-end learning system which can learn representations of face videos for the specific tasks. Experiments on two public face video datasets demonstrate the effectiveness of the proposed network.