Xianzheng Ma

Yulu Gan, Yan Bai, Yihang Lou et al. · pku

Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly focus on model-based adaptation in a self-training manner, such as predicting pseudo labels for new domain datasets. Since pseudo labels are noisy and unreliable, these methods suffer from catastrophic forgetting and error accumulation when dealing with dynamic data distributions. Motivated by the prompt learning in NLP, in this paper, we propose to learn an image-level visual domain prompt for target domains while having the source model parameters frozen. During testing, the changing target datasets can be adapted to the source model by reformulating the input data with the learned visual prompts. Specifically, we devise two types of prompts, i.e., domains-specific prompts and domains-agnostic prompts, to extract current domain knowledge and maintain the domain-shared knowledge in the continual adaptation. Furthermore, we design a homeostasis-based prompt adaptation strategy to suppress domain-sensitive parameters in domain-invariant prompts to learn domain-shared knowledge more effectively. This transition from the model-dependent paradigm to the model-free one enables us to bypass the catastrophic forgetting and error accumulation problems. Experiments show that our proposed method achieves significant performance gains over state-of-the-art methods on four widely-used benchmarks, including CIFAR-10C, CIFAR-100C, ImageNet-C, and VLCS datasets.

Ziyu Guo, Renrui Zhang, Longtian Qiu et al.

Contrastive Language-Image Pre-training (CLIP) has been shown to learn visual representations with great transferability, which achieves promising accuracy for zero-shot classification. To further improve its downstream performance, existing works propose additional learnable modules upon CLIP and fine-tune them by few-shot training sets. However, the resulting extra training cost and data requirement severely hinder the efficiency for model deployment and knowledge transfer. In this paper, we introduce a free-lunch enhancement method, CALIP, to boost CLIP's zero-shot performance via a parameter-free Attention module. Specifically, we guide visual and textual representations to interact with each other and explore cross-modal informative features via attention. As the pre-training has largely reduced the embedding distances between two modalities, we discard all learnable parameters in the attention and bidirectionally update the multi-modal features, enabling the whole process to be parameter-free and training-free. In this way, the images are blended with textual-aware signals and the text representations become visual-guided for better adaptive zero-shot alignment. We evaluate CALIP on various benchmarks of 14 datasets for both 2D image and 3D point cloud few-shot classification, showing consistent zero-shot performance improvement over CLIP. Based on that, we further insert a small number of linear layers in CALIP's attention module and verify our robustness under the few-shot settings, which also achieves leading performance compared to existing methods. Those extensive experiments demonstrate the superiority of our approach for efficient enhancement of CLIP.

Ziteng Cui, Lin Gu, Xiao Sun et al.

Common capture low-light scenes are challenging for most computer vision techniques, including Neural Radiance Fields (NeRF). Vanilla NeRF is viewer-centred simplifies the rendering process only as light emission from 3D locations in the viewing direction, thus failing to model the low-illumination induced darkness. Inspired by the emission theory of ancient Greeks that visual perception is accomplished by rays casting from eyes, we make slight modifications on vanilla NeRF to train on multiple views of low-light scenes, we can thus render out the well-lit scene in an unsupervised manner. We introduce a surrogate concept, Concealing Fields, that reduces the transport of light during the volume rendering stage. Specifically, our proposed method, Aleth-NeRF, directly learns from the dark image to understand volumetric object representation and concealing field under priors. By simply eliminating Concealing Fields, we can render a single or multi-view well-lit image(s) and gain superior performance over other 2D low-light enhancement methods. Additionally, we collect the first paired LOw-light and normal-light Multi-view (LOM) datasets for future research. This version is invalid, please refer to our new AAAI version: arXiv:2312.09093

Yihao Liu, Xiangyu Chen, Xianzheng Ma et al.

Image processing is a fundamental task in computer vision, which aims at enhancing image quality and extracting essential features for subsequent vision applications. Traditionally, task-specific models are developed for individual tasks and designing such models requires distinct expertise. Building upon the success of large language models (LLMs) in natural language processing (NLP), there is a similar trend in computer vision, which focuses on developing large-scale models through pretraining and in-context learning. This paradigm shift reduces the reliance on task-specific models, yielding a powerful unified model to deal with various tasks. However, these advances have predominantly concentrated on high-level vision tasks, with less attention paid to low-level vision tasks. To address this issue, we propose a universal model for general image processing that covers image restoration, image enhancement, image feature extraction tasks, etc. Our proposed framework, named PromptGIP, unifies these diverse image processing tasks within a universal framework. Inspired by NLP question answering (QA) techniques, we employ a visual prompting question answering paradigm. Specifically, we treat the input-output image pair as a structured question-answer sentence, thereby reprogramming the image processing task as a prompting QA problem. PromptGIP can undertake diverse cross-domain tasks using provided visual prompts, eliminating the need for task-specific finetuning. Our methodology offers a universal and adaptive solution to general image processing. While PromptGIP has demonstrated a certain degree of out-of-domain task generalization capability, further research is expected to fully explore its more powerful emergent generalization.

Xianzheng Ma, Tao Sun, Shuai Chen et al.

Recent 3D Large-Language Models (3D-LLMs) claim to understand 3D worlds, especially spatial relationships among objects. Yet, we find that simply fine-tuning a language model on text-only question-answer pairs can perform comparably or even surpass these methods on the SQA3D benchmark without using any 3D input. This indicates that the SQA3D benchmark may not be able to detect if the model exploits textual shortcuts rather than engages in 3D-aware reasoning. To address this issue, we introduce Real-3DQA, a more rigorous evaluation benchmark that filters out easy-to-guess questions and introduces a structured taxonomy to assess various aspects of 3D reasoning. Experiments on Real-3DQA confirm that existing 3D-LLMs struggle with spatial relationships once simple cues are removed. We further propose a 3D-reweighted training objective that guides model to rely more on 3D visual clues, substantially enhancing 3D-LLMs performance in spatial reasoning tasks. Our findings underscore the need for robust benchmarks and tailored training strategies to advance genuine 3D vision-language understanding. Project page: https://real-3dqa.github.io/.

Ziteng Cui, Lin Gu, Xiao Sun et al.

The standard Neural Radiance Fields (NeRF) paradigm employs a viewer-centered methodology, entangling the aspects of illumination and material reflectance into emission solely from 3D points. This simplified rendering approach presents challenges in accurately modeling images captured under adverse lighting conditions, such as low light or over-exposure. Motivated by the ancient Greek emission theory that posits visual perception as a result of rays emanating from the eyes, we slightly refine the conventional NeRF framework to train NeRF under challenging light conditions and generate normal-light condition novel views unsupervised. We introduce the concept of a "Concealing Field," which assigns transmittance values to the surrounding air to account for illumination effects. In dark scenarios, we assume that object emissions maintain a standard lighting level but are attenuated as they traverse the air during the rendering process. Concealing Field thus compel NeRF to learn reasonable density and colour estimations for objects even in dimly lit situations. Similarly, the Concealing Field can mitigate over-exposed emissions during the rendering stage. Furthermore, we present a comprehensive multi-view dataset captured under challenging illumination conditions for evaluation. Our code and dataset available at https://github.com/cuiziteng/Aleth-NeRF

Xianzheng Ma, Brandon Smart, Yash Bhalgat et al. · bytedance, oxford

As large language models (LLMs) evolve, their integration with 3D spatial data (3D-LLMs) has seen rapid progress, offering unprecedented capabilities for understanding and interacting with physical spaces. This survey provides a comprehensive overview of the methodologies enabling LLMs to process, understand, and generate 3D data. Highlighting the unique advantages of LLMs, such as in-context learning, step-by-step reasoning, open-vocabulary capabilities, and extensive world knowledge, we underscore their potential to significantly advance spatial comprehension and interaction within embodied Artificial Intelligence (AI) systems. Our investigation spans various 3D data representations, from point clouds to Neural Radiance Fields (NeRFs). It examines their integration with LLMs for tasks such as 3D scene understanding, captioning, question-answering, and dialogue, as well as LLM-based agents for spatial reasoning, planning, and navigation. The paper also includes a brief review of other methods that integrate 3D and language. The meta-analysis presented in this paper reveals significant progress yet underscores the necessity for novel approaches to harness the full potential of 3D-LLMs. Hence, with this paper, we aim to chart a course for future research that explores and expands the capabilities of 3D-LLMs in understanding and interacting with the complex 3D world. To support this survey, we have established a project page where papers related to our topic are organized and listed: https://github.com/ActiveVisionLab/Awesome-LLM-3D.

Ziyang Gong, Fuhao Li, Yupeng Deng et al.

Unsupervised Domain Adaptation (UDA) aims to adapt models from labeled source domains to unlabeled target domains. When adapting to adverse scenes, existing UDA methods fail to perform well due to the lack of instructions, leading their models to overlook discrepancies within all adverse scenes. To tackle this, we propose CoDA which instructs models to distinguish, focus, and learn from these discrepancies at scene and image levels. Specifically, CoDA consists of a Chain-of-Domain (CoD) strategy and a Severity-Aware Visual Prompt Tuning (SAVPT) mechanism. CoD focuses on scene-level instructions to divide all adverse scenes into easy and hard scenes, guiding models to adapt from source to easy domains with easy scene images, and then to hard domains with hard scene images, thereby laying a solid foundation for whole adaptations. Building upon this foundation, we employ SAVPT to dive into more detailed image-level instructions to boost performance. SAVPT features a novel metric Severity that divides all adverse scene images into low-severity and high-severity images. Then Severity directs visual prompts and adapters, instructing models to concentrate on unified severity features instead of scene-specific features, without adding complexity to the model architecture. CoDA achieves SOTA performances on widely-used benchmarks under all adverse scenes. Notably, CoDA outperforms the existing ones by 4.6%, and 10.3% mIoU on the Foggy Driving, and Foggy Zurich benchmarks, respectively. Our code is available at https://github.com/Cuzyoung/CoDA

Yongchang Zhang, Xianzheng Ma, Tianyi Liu et al.

Recent large vision-language models (LVLMs) have demonstrated impressive reasoning ability by generating long chain-of-thought (CoT) responses. However, CoT reasoning in multimodal contexts is highly vulnerable to visual hallucination propagation: once an intermediate reasoning step becomes inconsistent with the visual evidence, subsequent steps-even if logically valid-can still lead to incorrect final answers. Existing solutions attempt to mitigate this issue by training models to "think with images" via reinforcement learning (RL). While effective, these methods are costly, model-specific, and difficult to generalize across architectures. Differently, we present a lightweight method that bypasses RL training and provides an iterative, training-free, plug-and-play framework for visually-grounded multimodal reasoning. Our key idea is to supervise each reasoning step at test time with visual evidence, ensuring that every decoded token is justified by corresponding visual cues. Concretely, we construct a textual visual-evidence pool that guides the model's reasoning generation. When existing evidence is insufficient, a visual decider module dynamically extracts additional relevant evidence from the image based on the ongoing reasoning context, expanding the pool until the model achieves sufficient visual certainty to terminate reasoning and produce the final answer. Extensive experiments on multiple LVLM backbones and benchmarks demonstrate the effectiveness of our approach. Our method achieves 16.5%-29.5% improvements on TreeBench and 13.7% RH-AUC gains on RH-Bench, substantially reducing hallucination rates while improving reasoning accuracy without additional training.

Ziyu Guo, Renrui Zhang, Xiangyang Zhu et al.

We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising applications, e.g., any-to-3D generation, 3D embedding arithmetic, and 3D open-world understanding. On top of this, we further present Point-LLM, the first 3D large language model (LLM) following 3D multi-modal instructions. By parameter-efficient fine-tuning techniques, Point-LLM injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi-modal question-answering capacity. We hope our work may cast a light on the community for extending 3D point clouds to multi-modality applications. Code is available at https://github.com/ZiyuGuo99/Point-Bind_Point-LLM.

Renrui Zhang, Zhengkai Jiang, Ziyu Guo et al.

Driven by large-data pre-training, Segment Anything Model (SAM) has been demonstrated as a powerful and promptable framework, revolutionizing the segmentation models. Despite the generality, customizing SAM for specific visual concepts without man-powered prompting is under explored, e.g., automatically segmenting your pet dog in different images. In this paper, we propose a training-free Personalization approach for SAM, termed as PerSAM. Given only a single image with a reference mask, PerSAM first localizes the target concept by a location prior, and segments it within other images or videos via three techniques: target-guided attention, target-semantic prompting, and cascaded post-refinement. In this way, we effectively adapt SAM for private use without any training. To further alleviate the mask ambiguity, we present an efficient one-shot fine-tuning variant, PerSAM-F. Freezing the entire SAM, we introduce two learnable weights for multi-scale masks, only training 2 parameters within 10 seconds for improved performance. To demonstrate our efficacy, we construct a new segmentation dataset, PerSeg, for personalized evaluation, and test our methods on video object segmentation with competitive performance. Besides, our approach can also enhance DreamBooth to personalize Stable Diffusion for text-to-image generation, which discards the background disturbance for better target appearance learning. Code is released at https://github.com/ZrrSkywalker/Personalize-SAM

Ziyang Gong, Zhixiang Wei, Di Wang et al.

The field of Remote Sensing Domain Generalization (RSDG) has emerged as a critical and valuable research frontier, focusing on developing models that generalize effectively across diverse scenarios. Despite the substantial domain gaps in RS images that are characterized by variabilities such as location, wavelength, and sensor type, research in this area remains underexplored: (1) Current cross-domain methods primarily focus on Domain Adaptation (DA), which adapts models to predefined domains rather than to unseen ones; (2) Few studies targeting the RSDG issue, especially for semantic segmentation tasks, where existing models are developed for specific unknown domains, struggling with issues of underfitting on other unknown scenarios; (3) Existing RS foundation models tend to prioritize in-domain performance over cross-domain generalization. To this end, we introduce the first vision foundation model for RSDG semantic segmentation, CrossEarth. CrossEarth demonstrates strong cross-domain generalization through a specially designed data-level Earth-Style Injection pipeline and a model-level Multi-Task Training pipeline. In addition, for the semantic segmentation task, we have curated an RSDG benchmark comprising 32 cross-domain settings across various regions, spectral bands, platforms, and climates, providing a comprehensive framework for testing the generalizability of future RSDG models. Extensive experiments on this benchmark demonstrate the superiority of CrossEarth over existing state-of-the-art methods.

Yanbang Li, Ziyang Gong, Haoyang Li et al.

Recently, natural language has been the primary medium for human-robot interaction. However, its inherent lack of spatial precision introduces challenges for robotic task definition such as ambiguity and verbosity. Moreover, in some public settings where quiet is required, such as libraries or hospitals, verbal communication with robots is inappropriate. To address these limitations, we introduce the Robotic Visual Instruction (RoVI), a novel paradigm to guide robotic tasks through an object-centric, hand-drawn symbolic representation. RoVI effectively encodes spatial-temporal information into human-interpretable visual instructions through 2D sketches, utilizing arrows, circles, colors, and numbers to direct 3D robotic manipulation. To enable robots to understand RoVI better and generate precise actions based on RoVI, we present Visual Instruction Embodied Workflow (VIEW), a pipeline formulated for RoVI-conditioned policies. This approach leverages Vision-Language Models (VLMs) to interpret RoVI inputs, decode spatial and temporal constraints from 2D pixel space via keypoint extraction, and then transform them into executable 3D action sequences. We additionally curate a specialized dataset of 15K instances to fine-tune small VLMs for edge deployment,enabling them to effectively learn RoVI capabilities. Our approach is rigorously validated across 11 novel tasks in both real and simulated environments, demonstrating significant generalization capability. Notably, VIEW achieves an 87.5% success rate in real-world scenarios involving unseen tasks that feature multi-step actions, with disturbances, and trajectory-following requirements. Project website: https://robotic-visual-instruction.github.io/

Guanqi Zhan, Xianzheng Ma, Weidi Xie et al.

We study the task of predicting dynamic physical properties from videos. More specifically, we consider physical properties that require temporal information to be inferred: elasticity of a bouncing object, viscosity of a flowing liquid, and dynamic friction of an object sliding on a surface. To this end, we make the following contributions: (i) We collect a new video dataset for each physical property, consisting of synthetic training and testing splits, as well as a real split for real world evaluation. (ii) We explore three ways to infer the physical property from videos: (a) an oracle method where we supply the visual cues that intrinsically reflect the property using classical computer vision techniques; (b) a simple read out mechanism using a visual prompt and trainable prompt vector for cross-attention on pre-trained video generative and self-supervised models; and (c) prompt strategies for Multi-modal Large Language Models (MLLMs). (iii) We show that video foundation models trained in a generative or self-supervised manner achieve a similar performance, though behind that of the oracle, and MLLMs are currently inferior to the other models, though their performance can be improved through suitable prompting.

Jinjin Gu, Xianzheng Ma, Xiangtao Kong et al.

Deep deraining networks consistently encounter substantial generalization issues when deployed in real-world applications, although they are successful in laboratory benchmarks. A prevailing perspective in deep learning encourages using highly complex data for training, with the expectation that richer image background content will facilitate overcoming the generalization problem. However, through comprehensive and systematic experimentation, we discover that this strategy does not enhance the generalization capability of these networks. On the contrary, it exacerbates the tendency of networks to overfit specific degradations. Our experiments reveal that better generalization in a deraining network can be achieved by simplifying the complexity of the training background images. This is because that the networks are ``slacking off'' during training, that is, learning the least complex elements in the image background and degradation to minimize training loss. When the background images are less complex than the rain streaks, the network will prioritize the background reconstruction, thereby suppressing overfitting the rain patterns and leading to improved generalization performance. Our research offers a valuable perspective and methodology for better understanding the generalization problem in low-level vision tasks and displays promising potential for practical application.

Xianzheng Ma, Zhixiang Wang, Yacheng Zhan et al.

Although considerable progress has been made in semantic scene understanding under clear weather, it is still a tough problem under adverse weather conditions, such as dense fog, due to the uncertainty caused by imperfect observations. Besides, difficulties in collecting and labeling foggy images hinder the progress of this field. Considering the success in semantic scene understanding under clear weather, we think it is reasonable to transfer knowledge learned from clear images to the foggy domain. As such, the problem becomes to bridge the domain gap between clear images and foggy images. Unlike previous methods that mainly focus on closing the domain gap caused by fog -- defogging the foggy images or fogging the clear images, we propose to alleviate the domain gap by considering fog influence and style variation simultaneously. The motivation is based on our finding that the style-related gap and the fog-related gap can be divided and closed respectively, by adding an intermediate domain. Thus, we propose a new pipeline to cumulatively adapt style, fog and the dual-factor (style and fog). Specifically, we devise a unified framework to disentangle the style factor and the fog factor separately, and then the dual-factor from images in different domains. Furthermore, we collaborate the disentanglement of three factors with a novel cumulative loss to thoroughly disentangle these three factors. Our method achieves the state-of-the-art performance on three benchmarks and shows generalization ability in rainy and snowy scenes.