Recent advancements in controllable human image generation have led to zero-shot generation using structural signals (e.g., pose, depth) or facial appearance. Yet, generating human images conditioned on multiple parts of human appearance remains challenging. Addressing this, we introduce Parts2Whole, a novel framework designed for generating customized portraits from multiple reference images, including pose images and various aspects of human appearance. To achieve this, we first develop a semantic-aware appearance encoder to retain details of different human parts, which processes each image based on its textual label to a series of multi-scale feature maps rather than one image token, preserving the image dimension. Second, our framework supports multi-image conditioned generation through a shared self-attention mechanism that operates across reference and target features during the diffusion process. We enhance the vanilla attention mechanism by incorporating mask information from the reference human images, allowing for the precise selection of any part. Extensive experiments demonstrate the superiority of our approach over existing alternatives, offering advanced capabilities for multi-part controllable human image customization. See our project page at https://huanngzh.github.io/Parts2Whole/.
Nighttime self-supervised monocular depth estimation has received increasing attention in recent years. However, using night images for self-supervision is unreliable because the photometric consistency assumption is usually violated in the videos taken under complex lighting conditions. Even with domain adaptation or photometric loss repair, performance is still limited by the poor supervision of night images on trainable networks. In this paper, we propose a self-supervised nighttime monocular depth estimation method that does not use any night images during training. Our framework utilizes day images as a stable source for self-supervision and applies physical priors (e.g., wave optics, reflection model and read-shot noise model) to compensate for some key day-night differences. With day-to-night data distribution compensation, our framework can be trained in an efficient one-stage self-supervised manner. Though no nighttime images are considered during training, qualitative and quantitative results demonstrate that our method achieves SoTA depth estimating results on the challenging nuScenes-Night and RobotCar-Night compared with existing methods.
The ultimate goals of robotic learning is to acquire a comprehensive and generalizable robotic system capable of performing both seen skills within the training distribution and unseen skills in novel environments. Recent progress in utilizing language models as high-level planners has demonstrated that the complexity of tasks can be reduced through decomposing them into primitive-level plans, making it possible to generalize on novel robotic tasks in a composable manner. Despite the promising future, the community is not yet adequately prepared for composable generalization agents, particularly due to the lack of primitive-level real-world robotic datasets. In this paper, we propose a primitive-level robotic dataset, namely RH20T-P, which contains about 33000 video clips covering 44 diverse and complicated robotic tasks. Each clip is manually annotated according to a set of meticulously designed primitive skills, facilitating the future development of composable generalization agents. To validate the effectiveness of RH20T-P, we also construct a potential and scalable agent based on RH20T-P, called RA-P. Equipped with two planners specialized in task decomposition and motion planning, RA-P can adapt to novel physical skills through composable generalization. Our website and videos can be found at https://sites.google.com/view/rh20t-primitive/main. Dataset and code will be made available soon.
Large Language Models (LLMs) aim to serve as versatile assistants aligned with human values, as defined by the principles of being helpful, honest, and harmless (hhh). However, in terms of Multimodal Large Language Models (MLLMs), despite their commendable performance in perception and reasoning tasks, their alignment with human values remains largely unexplored, given the complexity of defining hhh dimensions in the visual world and the difficulty in collecting relevant data that accurately mirrors real-world situations. To address this gap, we introduce Ch3Ef, a Compreh3ensive Evaluation dataset and strategy for assessing alignment with human expectations. Ch3Ef dataset contains 1002 human-annotated data samples, covering 12 domains and 46 tasks based on the hhh principle. We also present a unified evaluation strategy supporting assessment across various scenarios and different perspectives. Based on the evaluation results, we summarize over 10 key findings that deepen the understanding of MLLM capabilities, limitations, and the dynamic relationships between evaluation levels, guiding future advancements in the field.
It is a long-lasting goal to design a generalist-embodied agent that can follow diverse instructions in human-like ways. However, existing approaches often fail to steadily follow instructions due to difficulties in understanding abstract and sequential natural language instructions. To this end, we introduce MineDreamer, an open-ended embodied agent built upon the challenging Minecraft simulator with an innovative paradigm that enhances instruction-following ability in low-level control signal generation. Specifically, MineDreamer is developed on top of recent advances in Multimodal Large Language Models (MLLMs) and diffusion models, and we employ a Chain-of-Imagination (CoI) mechanism to envision the step-by-step process of executing instructions and translating imaginations into more precise visual prompts tailored to the current state; subsequently, the agent generates keyboard-and-mouse actions to efficiently achieve these imaginations, steadily following the instructions at each step. Extensive experiments demonstrate that MineDreamer follows single and multi-step instructions steadily, significantly outperforming the best generalist agent baseline and nearly doubling its performance. Moreover, qualitative analysis of the agent's imaginative ability reveals its generalization and comprehension of the open world.
Multi-modal Large Language Models (MLLMs) have shown impressive abilities in generating reasonable responses with respect to multi-modal contents. However, there is still a wide gap between the performance of recent MLLM-based applications and the expectation of the broad public, even though the most powerful OpenAI's GPT-4 and Google's Gemini have been deployed. This paper strives to enhance understanding of the gap through the lens of a qualitative study on the generalizability, trustworthiness, and causal reasoning capabilities of recent proprietary and open-source MLLMs across four modalities: ie, text, code, image, and video, ultimately aiming to improve the transparency of MLLMs. We believe these properties are several representative factors that define the reliability of MLLMs, in supporting various downstream applications. To be specific, we evaluate the closed-source GPT-4 and Gemini and 6 open-source LLMs and MLLMs. Overall we evaluate 230 manually designed cases, where the qualitative results are then summarized into 12 scores (ie, 4 modalities times 3 properties). In total, we uncover 14 empirical findings that are useful to understand the capabilities and limitations of both proprietary and open-source MLLMs, towards more reliable downstream multi-modal applications.
Deep learning models have the ability to extract rich knowledge from large-scale datasets. However, the sharing of data has become increasingly challenging due to concerns regarding data copyright and privacy. Consequently, this hampers the effective transfer of knowledge from existing data to novel downstream tasks and concepts. Zero-shot learning (ZSL) approaches aim to recognize new classes by transferring semantic knowledge learned from base classes. However, traditional generative ZSL methods often require access to real images from base classes and rely on manually annotated attributes, which presents challenges in terms of data restrictions and model scalability. To this end, this paper tackles a challenging and practical problem dubbed as data-free zero-shot learning (DFZSL), where only the CLIP-based base classes data pre-trained classifier is available for zero-shot classification. Specifically, we propose a generic framework for DFZSL, which consists of three main components. Firstly, to recover the virtual features of the base data, we model the CLIP features of base class images as samples from a von Mises-Fisher (vMF) distribution based on the pre-trained classifier. Secondly, we leverage the text features of CLIP as low-cost semantic information and propose a feature-language prompt tuning (FLPT) method to further align the virtual image features and textual features. Thirdly, we train a conditional generative model using the well-aligned virtual image features and corresponding semantic text features, enabling the generation of new classes features and achieve better zero-shot generalization. Our framework has been evaluated on five commonly used benchmarks for generalized ZSL, as well as 11 benchmarks for the base-to-new ZSL. The results demonstrate the superiority and effectiveness of our approach. Our code is available in https://github.com/ylong4/DFZSL
3D point cloud semantic segmentation has a wide range of applications. Recently, weakly supervised point cloud segmentation methods have been proposed, aiming to alleviate the expensive and laborious manual annotation process by leveraging scene-level labels. However, these methods have not effectively exploited the rich geometric information (such as shape and scale) and appearance information (such as color and texture) present in RGB-D scans. Furthermore, current approaches fail to fully leverage the point affinity that can be inferred from the feature extraction network, which is crucial for learning from weak scene-level labels. Additionally, previous work overlooks the detrimental effects of the long-tailed distribution of point cloud data in weakly supervised 3D semantic segmentation. To this end, this paper proposes a simple yet effective scene-level weakly supervised point cloud segmentation method with a newly introduced multi-modality point affinity inference module. The point affinity proposed in this paper is characterized by features from multiple modalities (e.g., point cloud and RGB), and is further refined by normalizing the classifier weights to alleviate the detrimental effects of long-tailed distribution without the need of the prior of category distribution. Extensive experiments on the ScanNet and S3DIS benchmarks verify the effectiveness of our proposed method, which outperforms the state-of-the-art by ~4% to ~6% mIoU. Codes are released at https://github.com/Sunny599/AAAI24-3DWSSG-MMA.
It is a long-lasting goal to design an embodied system that can solve long-horizon open-world tasks in human-like ways. However, existing approaches usually struggle with compound difficulties caused by the logic-aware decomposition and context-aware execution of these tasks. To this end, we introduce MP5, an open-ended multimodal embodied system built upon the challenging Minecraft simulator, which can decompose feasible sub-objectives, design sophisticated situation-aware plans, and perform embodied action control, with frequent communication with a goal-conditioned active perception scheme. Specifically, MP5 is developed on top of recent advances in Multimodal Large Language Models (MLLMs), and the system is modulated into functional modules that can be scheduled and collaborated to ultimately solve pre-defined context- and process-dependent tasks. Extensive experiments prove that MP5 can achieve a 22% success rate on difficult process-dependent tasks and a 91% success rate on tasks that heavily depend on the context. Moreover, MP5 exhibits a remarkable ability to address many open-ended tasks that are entirely novel.
Generating multiview images from a single view facilitates the rapid generation of a 3D mesh conditioned on a single image. Recent methods that introduce 3D global representation into diffusion models have shown the potential to generate consistent multiviews, but they have reduced generation speed and face challenges in maintaining generalizability and quality. To address this issue, we propose EpiDiff, a localized interactive multiview diffusion model. At the core of the proposed approach is to insert a lightweight epipolar attention block into the frozen diffusion model, leveraging epipolar constraints to enable cross-view interaction among feature maps of neighboring views. The newly initialized 3D modeling module preserves the original feature distribution of the diffusion model, exhibiting compatibility with a variety of base diffusion models. Experiments show that EpiDiff generates 16 multiview images in just 12 seconds, and it surpasses previous methods in quality evaluation metrics, including PSNR, SSIM and LPIPS. Additionally, EpiDiff can generate a more diverse distribution of views, improving the reconstruction quality from generated multiviews. Please see our project page at https://huanngzh.github.io/EpiDiff/.