Zedong Zhang

Jun Li, Zedong Zhang, Jian Yang

Generating creative combinatorial objects from two seemingly unrelated object texts is a challenging task in text-to-image synthesis, often hindered by a focus on emulating existing data distributions. In this paper, we develop a straightforward yet highly effective method, called \textbf{balance swap-sampling}. First, we propose a swapping mechanism that generates a novel combinatorial object image set by randomly exchanging intrinsic elements of two text embeddings through a cutting-edge diffusion model. Second, we introduce a balance swapping region to efficiently sample a small subset from the newly generated image set by balancing CLIP distances between the new images and their original generations, increasing the likelihood of accepting the high-quality combinations. Last, we employ a segmentation method to compare CLIP distances among the segmented components, ultimately selecting the most promising object from the sampled subset. Extensive experiments demonstrate that our approach outperforms recent SOTA T2I methods. Surprisingly, our results even rival those of human artists, such as frog-broccoli.

Eric Stumpe, Miroslav Despotovic, Zedong Zhang et al.

The assessment and valuation of real estate requires large datasets with real estate information. Unfortunately, real estate databases are usually sparse in practice, i.e., not for each property every important attribute is available. In this paper, we study the potential of predicting high-level real estate attributes from visual data, specifically from two visual modalities, namely indoor (interior) and outdoor (facade) photos. We design three models using different multimodal fusion strategies and evaluate them for three different use cases. Thereby, a particular challenge is to handle missing modalities. We evaluate different fusion strategies, present baselines for the different prediction tasks, and find that enriching the training data with additional incomplete samples can lead to an improvement in prediction accuracy. Furthermore, the fusion of information from indoor and outdoor photos results in a performance boost of up to 5% in Macro F1-score.

Yiwen Chen, Sheng Guo, Zedong Zhang et al.

Precision robotic manipulation tasks (insertion, screwing, precisely pick, precisely place) are required in many scenarios. Previous methods achieved good performance on such manipulation tasks. However, such methods typically require tedious calibration or expensive sensors. 3D/RGB-D cameras and torque/force sensors add to the cost of the robotic application and may not always be economical. In this work, we aim to solve these but using only weak-calibrated and low-cost webcams. We propose Binocular Alignment Learning (BAL), which could automatically learn the eye-hand coordination and points alignment capabilities to solve the four tasks. Our work focuses on working with unknown eye-hand coordination and proposes different ways of performing eye-in-hand camera calibration automatically. The algorithm was trained in simulation and used a practical pipeline to achieve sim2real and test it on the real robot. Our method achieves a competitively good result with minimal cost on the four tasks.

Yiwen Chen, Zedong Zhang, Haofeng Liu et al.

In recent years, a myriad of superlative works on intelligent robotics policies have been done, thanks to advances in machine learning. However, inefficiency and lack of transfer ability hindered algorithms from pragmatic applications, especially in human-robot collaboration, when few-shot fast learning and high flexibility become a wherewithal. To surmount this obstacle, we refer to a "Policy Pool", containing pre-trained skills that can be easily accessed and reused. An agent is employed to govern the "Policy Pool" by unfolding requisite skills in a flexible sequence, contingent on task specific predilection. This predilection can be automatically interpreted from one or few human expert demonstrations. Under this hierarchical setting, our algorithm is able to pick up a sparse-reward, multi-stage knack with only one demonstration in a Mini-Grid environment, showing the potential for instantly mastering complex robotics skills from human instructors. Additionally, the innate quality of our algorithm also allows for lifelong learning, making it a versatile agent.

Zeren Xiong, Zedong Zhang, Zikun Chen et al.

In this paper, we study an object synthesis task that combines an object text with an object image to create a new object image. However, most diffusion models struggle with this task, \textit{i.e.}, often generating an object that predominantly reflects either the text or the image due to an imbalance between their inputs. To address this issue, we propose a simple yet effective method called Adaptive Text-Image Harmony (ATIH) to generate novel and surprising objects. First, we introduce a scale factor and an injection step to balance text and image features in cross-attention and to preserve image information in self-attention during the text-image inversion diffusion process, respectively. Second, to better integrate object text and image, we design a balanced loss function with a noise parameter, ensuring both optimal editability and fidelity of the object image. Third, to adaptively adjust these parameters, we present a novel similarity score function that not only maximizes the similarities between the generated object image and the input text/image but also balances these similarities to harmonize text and image integration. Extensive experiments demonstrate the effectiveness of our approach, showcasing remarkable object creations such as colobus-glass jar. Project page: https://xzr52.github.io/ATIH/.

Zeren Xiong, Zikun Chen, Zedong Zhang et al.

In this paper, we tackle a new task of 3D object synthesis, where a 3D model is composited with another object category to create a novel 3D model. However, most existing text/image/3D-to-3D methods struggle to effectively integrate multiple content sources, often resulting in inconsistent textures and inaccurate shapes. To overcome these challenges, we propose a straightforward yet powerful approach, category+3D-to-3D (C33D), for generating novel and structurally coherent 3D models. Our method begins by rendering multi-view images and normal maps from the input 3D model, then generating a novel 2D object using adaptive text-image harmony (ATIH) with the front-view image and a text description from another object category as inputs. To ensure texture consistency, we introduce texture multi-view diffusion, which refines the textures of the remaining multi-view RGB images based on the novel 2D object. For enhanced shape accuracy, we propose shape multi-view diffusion to improve the 2D shapes of both the multi-view RGB images and the normal maps, also conditioned on the novel 2D object. Finally, these outputs are used to reconstruct a complete and novel 3D model. Extensive experiments demonstrate the effectiveness of our method, yielding impressive 3D creations, such as shark(3D)-crocodile(text) in the first row of Fig. 1. A project page is available at: https://xzr52.github.io/C33D/

Zeren Xiong, Yue Yu, Zedong Zhang et al.

Creating novel images by fusing visual cues from multiple sources is a fundamental yet underexplored problem in image-to-image generation, with broad applications in artistic creation, virtual reality and visual media. Existing methods often face two key challenges: coexistent generation, where multiple objects are simply juxtaposed without true integration, and bias generation, where one object dominates the output due to semantic imbalance. To address these issues, we propose Visual Mixing Diffusion (VMDiff), a simple yet effective diffusion-based framework that synthesizes a single, coherent object by integrating two input images at both noise and latent levels. Our approach comprises: (1) a hybrid sampling process that combines guided denoising, inversion, and spherical interpolation with adjustable parameters to achieve structure-aware fusion, mitigating coexistent generation; and (2) an efficient adaptive adjustment module, which introduces a novel similarity-based score to automatically and adaptively search for optimal parameters, countering semantic bias. Experiments on a curated benchmark of 780 concept pairs demonstrate that our method outperforms strong baselines in visual quality, semantic consistency, and human-rated creativity.

Zedong Zhang, Ying Tai, Jianjun Qian et al.

Fusing cross-category objects to a single coherent object has gained increasing attention in text-to-image (T2I) generation due to its broad applications in virtual reality, digital media, film, and gaming. However, existing methods often produce biased, visually chaotic, or semantically inconsistent results due to overlapping artifacts and poor integration. Moreover, progress in this field has been limited by the absence of a comprehensive benchmark dataset. To address these problems, we propose \textbf{Adaptive Group Swapping (AGSwap)}, a simple yet highly effective approach comprising two key components: (1) Group-wise Embedding Swapping, which fuses semantic attributes from different concepts through feature manipulation, and (2) Adaptive Group Updating, a dynamic optimization mechanism guided by a balance evaluation score to ensure coherent synthesis. Additionally, we introduce \textbf{Cross-category Object Fusion (COF)}, a large-scale, hierarchically structured dataset built upon ImageNet-1K and WordNet. COF includes 95 superclasses, each with 10 subclasses, enabling 451,250 unique fusion pairs. Extensive experiments demonstrate that AGSwap outperforms state-of-the-art compositional T2I methods, including GPT-Image-1 using simple and complex prompts.

Miroslav Despotovic, Zedong Zhang, Eric Stumpe et al.

We describe a proof-of-concept for annotating real estate images using simple iterative rule-based semi-supervised learning. In this study, we have gained important insights into the content characteristics and uniqueness of individual image classes as well as essential requirements for a practical implementation.