Abstract:Recent advances in text-to-image model customization have underscored the importance of integrating new concepts with a few examples. Yet, these progresses are largely confined to widely recognized subjects, which can be learned with relative ease through models' adequate shared prior knowledge. In contrast, logos, characterized by unique patterns and textual elements, are hard to establish shared knowledge within diffusion models, thus presenting a unique challenge. To bridge this gap, we introduce the task of logo insertion. Our goal is to insert logo identities into diffusion models and enable their seamless synthesis in varied contexts. We present a novel two-phase pipeline LogoSticker to tackle this task. First, we propose the actor-critic relation pre-training algorithm, which addresses the nontrivial gaps in models' understanding of the potential spatial positioning of logos and interactions with other objects. Second, we propose a decoupled identity learning algorithm, which enables precise localization and identity extraction of logos. LogoSticker can generate logos accurately and harmoniously in diverse contexts. We comprehensively validate the effectiveness of LogoSticker over customization methods and large models such as DALLE~3. \href{https://mingkangz.github.io/logosticker}{Project page}.
Abstract:Although video perception models have made remarkable advancements in recent years, they still heavily rely on explicit text descriptions or pre-defined categories to identify target instances before executing video perception tasks. These models, however, fail to proactively comprehend and reason the user's intentions via textual input. Even though previous works attempt to investigate solutions to incorporate reasoning with image segmentation, they fail to reason with videos due to the video's complexity in object motion. To bridge the gap between image and video, in this work, we propose a new video segmentation task - video reasoning segmentation. The task is designed to output tracklets of segmentation masks given a complex input text query. What's more, to promote research in this unexplored area, we construct a reasoning video segmentation benchmark. Finally, we present ViLLa: Video reasoning segmentation with a Large Language Model, which incorporates the language generation capabilities of multimodal Large Language Models (LLMs) while retaining the capabilities of detecting, segmenting, and tracking multiple instances. We use a temporal-aware context aggregation module to incorporate contextual visual cues to text embeddings and propose a video-frame decoder to build temporal correlations across segmentation tokens. Remarkably, our ViLLa demonstrates capability in handling complex reasoning and referring video segmentation. Also, our model shows impressive ability in different temporal understanding benchmarks. Both quantitative and qualitative experiments show our method effectively unlocks new video reasoning segmentation capabilities for multimodal LLMs. The code and dataset will be available at https://github.com/rkzheng99/ViLLa.
Abstract:Recently, human-computer interaction with various modalities has shown promising applications, like GPT-4o and Gemini. Given the foundational role of multimodal joint representation in understanding and generation pipelines, high-quality omni joint representations would be a step toward co-processing more diverse multimodal information. In this work, we present OmniBind, large-scale multimodal joint representation models ranging in scale from 7 billion to 30 billion parameters, which support 3D, audio, image, and language inputs. Due to the scarcity of data pairs across all modalities, instead of training large models from scratch, we propose remapping and binding the spaces of various pre-trained specialist models together. This approach enables "scaling up" by indirectly increasing the model parameters and the amount of seen data. To effectively integrate various spaces, we dynamically assign weights to different spaces by learning routers with two objectives: cross-modal overall alignment and language representation decoupling. Notably, since binding and routing spaces both only require lightweight networks, OmniBind is extremely training-efficient. Learning the largest 30B model requires merely unpaired unimodal data and approximately 3 days on a single 8-4090 node. Extensive experiments demonstrate the versatility and superiority of OmniBind as an omni representation model, highlighting its great potential for diverse applications, such as any-query and composable multimodal understanding.
Abstract:High-resolution inputs enable Large Vision-Language Models (LVLMs) to discern finer visual details, enhancing their comprehension capabilities. To reduce the training and computation costs caused by high-resolution input, one promising direction is to use sliding windows to slice the input into uniform patches, each matching the input size of the well-trained vision encoder. Although efficient, this slicing strategy leads to the fragmentation of original input, i.e., the continuity of contextual information and spatial geometry is lost across patches, adversely affecting performance in cross-patch context perception and position-specific tasks. To overcome these shortcomings, we introduce HiRes-LLaVA, a novel framework designed to efficiently process any size of high-resolution input without altering the original contextual and geometric information. HiRes-LLaVA comprises two innovative components: (i) a SliceRestore adapter that reconstructs sliced patches into their original form, efficiently extracting both global and local features via down-up-sampling and convolution layers, and (ii) a Self-Mining Sampler to compresses the vision tokens based on themselves, preserving the original context and positional information while reducing training overhead. To assess the ability of handling context fragmentation, we construct a new benchmark, EntityGrid-QA, consisting of edge-related and position-related tasks. Our comprehensive experiments demonstrate the superiority of HiRes-LLaVA on both existing public benchmarks and on EntityGrid-QA, particularly on document-oriented tasks, establishing new standards for handling high-resolution inputs.
Abstract:Recent advances in 3D AIGC have shown promise in directly creating 3D objects from text and images, offering significant cost savings in animation and product design. However, detailed edit and customization of 3D assets remains a long-standing challenge. Specifically, 3D Generation methods lack the ability to follow finely detailed instructions as precisely as their 2D image creation counterparts. Imagine you can get a toy through 3D AIGC but with undesired accessories and dressing. To tackle this challenge, we propose a novel pipeline called Tailor3D, which swiftly creates customized 3D assets from editable dual-side images. We aim to emulate a tailor's ability to locally change objects or perform overall style transfer. Unlike creating 3D assets from multiple views, using dual-side images eliminates conflicts on overlapping areas that occur when editing individual views. Specifically, it begins by editing the front view, then generates the back view of the object through multi-view diffusion. Afterward, it proceeds to edit the back views. Finally, a Dual-sided LRM is proposed to seamlessly stitch together the front and back 3D features, akin to a tailor sewing together the front and back of a garment. The Dual-sided LRM rectifies imperfect consistencies between the front and back views, enhancing editing capabilities and reducing memory burdens while seamlessly integrating them into a unified 3D representation with the LoRA Triplane Transformer. Experimental results demonstrate Tailor3D's effectiveness across various 3D generation and editing tasks, including 3D generative fill and style transfer. It provides a user-friendly, efficient solution for editing 3D assets, with each editing step taking only seconds to complete.
Abstract:This study addresses the Domain-Class Incremental Learning problem, a realistic but challenging continual learning scenario where both the domain distribution and target classes vary across tasks. To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability. However, this incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability. Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy computation overhead. To address this problem efficiently, we propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of VLMs from a perspective of avoiding information interference. Specifically, we design a fully residual mechanism to infuse newly learned knowledge into a frozen backbone, while introducing minimal adverse impacts on pre-trained knowledge. Besides, this residual property enables our distribution-aware integration calibration scheme, explicitly controlling the information implantation process for test data from unseen distributions. Experiments demonstrate that our DIKI surpasses the current state-of-the-art approach using only 0.86% of the trained parameters and requiring substantially less training time. Code is available at: https://github.com/lloongx/DIKI .
Abstract:This work presents Depth Anything V2. Without pursuing fancy techniques, we aim to reveal crucial findings to pave the way towards building a powerful monocular depth estimation model. Notably, compared with V1, this version produces much finer and more robust depth predictions through three key practices: 1) replacing all labeled real images with synthetic images, 2) scaling up the capacity of our teacher model, and 3) teaching student models via the bridge of large-scale pseudo-labeled real images. Compared with the latest models built on Stable Diffusion, our models are significantly more efficient (more than 10x faster) and more accurate. We offer models of different scales (ranging from 25M to 1.3B params) to support extensive scenarios. Benefiting from their strong generalization capability, we fine-tune them with metric depth labels to obtain our metric depth models. In addition to our models, considering the limited diversity and frequent noise in current test sets, we construct a versatile evaluation benchmark with precise annotations and diverse scenes to facilitate future research.
Abstract:Image editing serves as a practical yet challenging task considering the diverse demands from users, where one of the hardest parts is to precisely describe how the edited image should look like. In this work, we present a new form of editing, termed imitative editing, to help users exercise their creativity more conveniently. Concretely, to edit an image region of interest, users are free to directly draw inspiration from some in-the-wild references (e.g., some relative pictures come across online), without having to cope with the fit between the reference and the source. Such a design requires the system to automatically figure out what to expect from the reference to perform the editing. For this purpose, we propose a generative training framework, dubbed MimicBrush, which randomly selects two frames from a video clip, masks some regions of one frame, and learns to recover the masked regions using the information from the other frame. That way, our model, developed from a diffusion prior, is able to capture the semantic correspondence between separate images in a self-supervised manner. We experimentally show the effectiveness of our method under various test cases as well as its superiority over existing alternatives. We also construct a benchmark to facilitate further research.
Abstract:Due to the need to interact with the real world, embodied agents are required to possess comprehensive prior knowledge, long-horizon planning capability, and a swift response speed. Despite recent large language model (LLM) based agents achieving promising performance, they still exhibit several limitations. For instance, the output of LLMs is a descriptive sentence, which is ambiguous when determining specific actions. To address these limitations, we introduce the large auto-regressive model (LARM). LARM leverages both text and multi-view images as input and predicts subsequent actions in an auto-regressive manner. To train LARM, we develop a novel data format named auto-regressive node transmission structure and assemble a corresponding dataset. Adopting a two-phase training regimen, LARM successfully harvests enchanted equipment in Minecraft, which demands significantly more complex decision-making chains than the highest achievements of prior best methods. Besides, the speed of LARM is 6.8x faster.
Abstract:In the current state of 3D object detection research, the severe scarcity of annotated 3D data, substantial disparities across different data modalities, and the absence of a unified architecture, have impeded the progress towards the goal of universality. In this paper, we propose \textbf{OV-Uni3DETR}, a unified open-vocabulary 3D detector via cycle-modality propagation. Compared with existing 3D detectors, OV-Uni3DETR offers distinct advantages: 1) Open-vocabulary 3D detection: During training, it leverages various accessible data, especially extensive 2D detection images, to boost training diversity. During inference, it can detect both seen and unseen classes. 2) Modality unifying: It seamlessly accommodates input data from any given modality, effectively addressing scenarios involving disparate modalities or missing sensor information, thereby supporting test-time modality switching. 3) Scene unifying: It provides a unified multi-modal model architecture for diverse scenes collected by distinct sensors. Specifically, we propose the cycle-modality propagation, aimed at propagating knowledge bridging 2D and 3D modalities, to support the aforementioned functionalities. 2D semantic knowledge from large-vocabulary learning guides novel class discovery in the 3D domain, and 3D geometric knowledge provides localization supervision for 2D detection images. OV-Uni3DETR achieves the state-of-the-art performance on various scenarios, surpassing existing methods by more than 6\% on average. Its performance using only RGB images is on par with or even surpasses that of previous point cloud based methods. Code and pre-trained models will be released later.