Augmenting Image Annotation: A Human-LMM Collaborative Framework for Efficient Object Selection and Label Generation

Traditional image annotation tasks rely heavily on human effort for object selection and label assignment, making the process time-consuming and prone to decreased efficiency as annotators experience fatigue after extensive work. This paper introduces a novel framework that leverages the visual understanding capabilities of large multimodal models (LMMs), particularly GPT, to assist annotation workflows. In our proposed approach, human annotators focus on selecting objects via bounding boxes, while the LMM autonomously generates relevant labels. This human-AI collaborative framework enhances annotation efficiency by reducing the cognitive and time burden on human annotators. By analyzing the system's performance across various types of annotation tasks, we demonstrate its ability to generalize to tasks such as object recognition, scene description, and fine-grained categorization. Our proposed framework highlights the potential of this approach to redefine annotation workflows, offering a scalable and efficient solution for large-scale data labeling in computer vision. Finally, we discuss how integrating LMMs into the annotation pipeline can advance bidirectional human-AI alignment, as well as the challenges of alleviating the "endless annotation" burden in the face of information overload by shifting some of the work to AI.

One-Step Diffusion Model for Image Motion-Deblurring

Currently, methods for single-image deblurring based on CNNs and transformers have demonstrated promising performance. However, these methods often suffer from perceptual limitations, poor generalization ability, and struggle with heavy or complex blur. While diffusion-based methods can partially address these shortcomings, their multi-step denoising process limits their practical usage. In this paper, we conduct an in-depth exploration of diffusion models in deblurring and propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step, significantly improving inference efficiency while maintaining high fidelity. To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration. Additionally, we construct a high-quality synthetic deblurring dataset to mitigate perceptual collapse and design a dynamic dual-adapter (DDA) to enhance perceptual quality while preserving fidelity. Extensive experiments demonstrate that our method achieves strong performance on both full and no-reference metrics. Our code and pre-trained model will be publicly available at https://github.com/xyLiu339/OSDD.

Benchmarking Zero-Shot Facial Emotion Annotation with Large Language Models: A Multi-Class and Multi-Frame Approach in DailyLife

This study investigates the feasibility and performance of using large language models (LLMs) to automatically annotate human emotions in everyday scenarios. We conducted experiments on the DailyLife subset of the publicly available FERV39k dataset, employing the GPT-4o-mini model for rapid, zero-shot labeling of key frames extracted from video segments. Under a seven-class emotion taxonomy ("Angry," "Disgust," "Fear," "Happy," "Neutral," "Sad," "Surprise"), the LLM achieved an average precision of approximately 50%. In contrast, when limited to ternary emotion classification (negative/neutral/positive), the average precision increased to approximately 64%. Additionally, we explored a strategy that integrates multiple frames within 1-2 second video clips to enhance labeling performance and reduce costs. The results indicate that this approach can slightly improve annotation accuracy. Overall, our preliminary findings highlight the potential application of zero-shot LLMs in human facial emotion annotation tasks, offering new avenues for reducing labeling costs and broadening the applicability of LLMs in complex multimodal environments.

Multitwine: Multi-Object Compositing with Text and Layout Control

We introduce the first generative model capable of simultaneous multi-object compositing, guided by both text and layout. Our model allows for the addition of multiple objects within a scene, capturing a range of interactions from simple positional relations (e.g., next to, in front of) to complex actions requiring reposing (e.g., hugging, playing guitar). When an interaction implies additional props, like `taking a selfie', our model autonomously generates these supporting objects. By jointly training for compositing and subject-driven generation, also known as customization, we achieve a more balanced integration of textual and visual inputs for text-driven object compositing. As a result, we obtain a versatile model with state-of-the-art performance in both tasks. We further present a data generation pipeline leveraging visual and language models to effortlessly synthesize multimodal, aligned training data.

TransPixar: Advancing Text-to-Video Generation with Transparency

Text-to-video generative models have made significant strides, enabling diverse applications in entertainment, advertising, and education. However, generating RGBA video, which includes alpha channels for transparency, remains a challenge due to limited datasets and the difficulty of adapting existing models. Alpha channels are crucial for visual effects (VFX), allowing transparent elements like smoke and reflections to blend seamlessly into scenes. We introduce TransPixar, a method to extend pretrained video models for RGBA generation while retaining the original RGB capabilities. TransPixar leverages a diffusion transformer (DiT) architecture, incorporating alpha-specific tokens and using LoRA-based fine-tuning to jointly generate RGB and alpha channels with high consistency. By optimizing attention mechanisms, TransPixar preserves the strengths of the original RGB model and achieves strong alignment between RGB and alpha channels despite limited training data. Our approach effectively generates diverse and consistent RGBA videos, advancing the possibilities for VFX and interactive content creation.

Text2Relight: Creative Portrait Relighting with Text Guidance

We present a lighting-aware image editing pipeline that, given a portrait image and a text prompt, performs single image relighting. Our model modifies the lighting and color of both the foreground and background to align with the provided text description. The unbounded nature in creativeness of a text allows us to describe the lighting of a scene with any sensory features including temperature, emotion, smell, time, and so on. However, the modeling of such mapping between the unbounded text and lighting is extremely challenging due to the lack of dataset where there exists no scalable data that provides large pairs of text and relighting, and therefore, current text-driven image editing models does not generalize to lighting-specific use cases. We overcome this problem by introducing a novel data synthesis pipeline: First, diverse and creative text prompts that describe the scenes with various lighting are automatically generated under a crafted hierarchy using a large language model (*e.g.,* ChatGPT). A text-guided image generation model creates a lighting image that best matches the text. As a condition of the lighting images, we perform image-based relighting for both foreground and background using a single portrait image or a set of OLAT (One-Light-at-A-Time) images captured from lightstage system. Particularly for the background relighting, we represent the lighting image as a set of point lights and transfer them to other background images. A generative diffusion model learns the synthesized large-scale data with auxiliary task augmentation (*e.g.,* portrait delighting and light positioning) to correlate the latent text and lighting distribution for text-guided portrait relighting.

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion

This paper addresses the critical need for democratizing large language models (LLM) in the Arab world, a region that has seen slower progress in developing models comparable to state-of-the-art offerings like GPT-4 or ChatGPT 3.5, due to a predominant focus on mainstream languages (e.g., English and Chinese). One practical objective for an Arabic LLM is to utilize an Arabic-specific vocabulary for the tokenizer that could speed up decoding. However, using a different vocabulary often leads to a degradation of learned knowledge since many words are initially out-of-vocabulary (OOV) when training starts. Inspired by the vocabulary learning during Second Language (Arabic) Acquisition for humans, the released AraLLaMA employs progressive vocabulary expansion, which is implemented by a modified BPE algorithm that progressively extends the Arabic subwords in its dynamic vocabulary during training, thereby balancing the OOV ratio at every stage. The ablation study demonstrated the effectiveness of Progressive Vocabulary Expansion. Moreover, AraLLaMA achieves decent performance comparable to the best Arabic LLMs across a variety of Arabic benchmarks. Models, training data, benchmarks, and codes will be all open-sourced.

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

We introduce UniReal, a unified framework designed to address various image generation and editing tasks. Existing solutions often vary by tasks, yet share fundamental principles: preserving consistency between inputs and outputs while capturing visual variations. Inspired by recent video generation models that effectively balance consistency and variation across frames, we propose a unifying approach that treats image-level tasks as discontinuous video generation. Specifically, we treat varying numbers of input and output images as frames, enabling seamless support for tasks such as image generation, editing, customization, composition, etc. Although designed for image-level tasks, we leverage videos as a scalable source for universal supervision. UniReal learns world dynamics from large-scale videos, demonstrating advanced capability in handling shadows, reflections, pose variation, and object interaction, while also exhibiting emergent capability for novel applications.

CHOICE: Coordinated Human-Object Interaction in Cluttered Environments for Pick-and-Place Actions

Animating human-scene interactions such as pick-and-place tasks in cluttered, complex layouts is a challenging task, with objects of a wide variation of geometries and articulation under scenarios with various obstacles. The main difficulty lies in the sparsity of the motion data compared to the wide variation of the objects and environments as well as the poor availability of transition motions between different tasks, increasing the complexity of the generalization to arbitrary conditions. To cope with this issue, we develop a system that tackles the interaction synthesis problem as a hierarchical goal-driven task. Firstly, we develop a bimanual scheduler that plans a set of keyframes for simultaneously controlling the two hands to efficiently achieve the pick-and-place task from an abstract goal signal such as the target object selected by the user. Next, we develop a neural implicit planner that generates guidance hand trajectories under diverse object shape/types and obstacle layouts. Finally, we propose a linear dynamic model for our DeepPhase controller that incorporates a Kalman filter to enable smooth transitions in the frequency domain, resulting in a more realistic and effective multi-objective control of the character.Our system can produce a wide range of natural pick-and-place movements with respect to the geometry of objects, the articulation of containers and the layout of the objects in the scene.

DIVE: Taming DINO for Subject-Driven Video Editing

Building on the success of diffusion models in image generation and editing, video editing has recently gained substantial attention. However, maintaining temporal consistency and motion alignment still remains challenging. To address these issues, this paper proposes DINO-guided Video Editing (DIVE), a framework designed to facilitate subject-driven editing in source videos conditioned on either target text prompts or reference images with specific identities. The core of DIVE lies in leveraging the powerful semantic features extracted from a pretrained DINOv2 model as implicit correspondences to guide the editing process. Specifically, to ensure temporal motion consistency, DIVE employs DINO features to align with the motion trajectory of the source video. Extensive experiments on diverse real-world videos demonstrate that our framework can achieve high-quality editing results with robust motion consistency, highlighting the potential of DINO to contribute to video editing. For precise subject editing, DIVE incorporates the DINO features of reference images into a pretrained text-to-image model to learn Low-Rank Adaptations (LoRAs), effectively registering the target subject's identity. Project page: https://dino-video-editing.github.io