Yancheng Bai

Xiangyan Qu, Zhenlong Yuan, Jing Tang et al. · tsinghua

Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) generation. Unlike T2I generation, image editing is goal-directed: the solution space is constrained by the source image and instruction. This mismatch causes three challenges when applying Image-CoT to editing: inefficient resource allocation with fixed sampling budgets, unreliable early-stage verification using general MLLM scores, and redundant edited results from large-scale sampling. To address this, we propose ADaptive Edit-CoT (ADE-CoT), an on-demand test-time scaling framework to enhance editing efficiency and performance. It incorporates three key strategies: (1) a difficulty-aware resource allocation that assigns dynamic budgets based on estimated edit difficulty; (2) edit-specific verification in early pruning that uses region localization and caption consistency to select promising candidates; and (3) depth-first opportunistic stopping, guided by an instance-specific verifier, that terminates when intent-aligned results are found. Extensive experiments on three SOTA editing models (Step1X-Edit, BAGEL, FLUX.1 Kontext) across three benchmarks show that ADE-CoT achieves superior performance-efficiency trade-offs. With comparable sampling budgets, ADE-CoT obtains better performance with more than 2x speedup over Best-of-N.

Rui Lan, Yancheng Bai, Xu Duan et al.

Scene text editing aims to modify or add texts on images while ensuring text fidelity and overall visual quality consistent with the background. Recent methods are primarily built on UNet-based diffusion models, which have improved scene text editing results, but still struggle with complex glyph structures, especially for non-Latin ones (\eg, Chinese, Korean, Japanese). To address these issues, we present \textbf{FLUX-Text}, a simple and advanced multilingual scene text editing DiT method. Specifically, our FLUX-Text enhances glyph understanding and generation through lightweight Visual and Text Embedding Modules, while preserving the original generative capability of FLUX. We further propose a Regional Text Perceptual Loss tailored for text regions, along with a matching two-stage training strategy to better balance text editing and overall image quality. Benefiting from the DiT-based architecture and lightweight feature injection modules, FLUX-Text can be trained with only $0.1$M training examples, a \textbf{97\%} reduction compared to $2.9$M required by popular methods. Extensive experiments on multiple public datasets, including English and Chinese benchmarks, demonstrate that our method surpasses other methods in visual quality and text fidelity. All the code is available at https://github.com/AMAP-ML/FluxText.

Ruidong Chen, Yancheng Bai, Xuanpu Zhang et al.

Region-instructed layout control in text-to-image generation is highly practical, yet existing methods suffer from limitations: (i) training-based approaches inherit data bias and often degrade image quality, and (ii) current techniques struggle with occlusion order, limiting real-world usability. To address these issues, we propose LayerBind. By modeling regional generation as distinct layers and binding them during the generation, our method enables precise regional and occlusion controllability. Our motivation stems from the observation that spatial layout and occlusion are established at a very early denoising stage, suggesting that rearranging the early latent structure is sufficient to modify the final output. Building on this, we structure the scheme into two phases: instance initialization and subsequent semantic nursing. (1) First, leveraging the contextual sharing mechanism in multimodal joint attention, Layer-wise Instance Initialization creates per-instance branches that attend to their own regions while anchoring to the shared background. At a designated early step, these branches are fused according to the layer order to form a unified latent with a pre-established layout. (2) Then, Layer-wise Semantic Nursing reinforces regional details and maintains the occlusion order via a layer-wise attention enhancement. Specifically, a sequential layered attention path operates alongside the standard global path, with updates composited under a layer-transparency scheduler. LayerBind is training-free and plug-and-play, serving as a regional and occlusion controller across Diffusion Transformers. Beyond generation, it natively supports editable workflows, allowing for flexible modifications like changing instances or rearranging visible orders. Both qualitative and quantitative results demonstrate LayerBind's effectiveness, highlighting its strong potential for creative applications.

Ryan Xu, Dongyang Jin, Yancheng Bai et al.

Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation remains challenging for Visual Autoregressive (VAR) models due to their hierarchical, next-scale prediction style. Existing VAR-based methods often suffer from inefficient control encoding and disruptive injection mechanisms that compromise both fidelity and efficiency. In this work, we present SCALAR, a controllable generation method based on VAR, incorporating a novel Scale-wise Conditional Decoding mechanism. SCALAR leverages a pretrained image encoder to extract semantic control signal encodings, which are projected into scale-specific representations and injected into the corresponding layers of the VAR backbone. This design provides persistent and structurally aligned guidance throughout the generation process. Building on SCALAR, we develop SCALAR-Uni, a unified extension that aligns multiple control modalities into a shared latent space, supporting flexible multi-conditional guidance in a single model. Extensive experiments show that SCALAR achieves superior generation quality and control precision across various tasks. The code is released at https://github.com/AMAP-ML/SCALAR.

Mingxing Li, Rui Wang, Lei Sun et al.

The rapid expansion of mobile internet has resulted in a substantial increase in user-generated content (UGC) images, thereby making the thorough assessment of UGC images both urgent and essential. Recently, multimodal large language models (MLLMs) have shown great potential in image quality assessment (IQA) and image aesthetic assessment (IAA). Despite this progress, effectively scoring the quality and aesthetics of UGC images still faces two main challenges: 1) A single score is inadequate to capture the hierarchical human perception. 2) How to use MLLMs to output numerical scores, such as mean opinion scores (MOS), remains an open question. To address these challenges, we introduce a novel dataset, named Realistic image Quality and Aesthetic (RealQA), including 14,715 UGC images, each of which is annoted with 10 fine-grained attributes. These attributes span three levels: low level (e.g., image clarity), middle level (e.g., subject integrity) and high level (e.g., composition). Besides, we conduct a series of in-depth and comprehensive investigations into how to effectively predict numerical scores using MLLMs. Surprisingly, by predicting just two extra significant digits, the next token paradigm can achieve SOTA performance. Furthermore, with the help of chain of thought (CoT) combined with the learnt fine-grained attributes, the proposed method can outperform SOTA methods on five public datasets for IQA and IAA with superior interpretability and show strong zero-shot generalization for video quality assessment (VQA). The code and dataset will be released.

Haodong He, Yancheng Bai, Rui Lan et al.

The rich textual information of large vision-language models (VLMs) combined with the powerful generative prior of pre-trained text-to-image (T2I) diffusion models has achieved impressive performance in single-image super-resolution (SISR). However, existing methods still face significant challenges in generating clear and accurate regional details, particularly in scenarios involving multiple objects. This challenge primarily stems from a lack of fine-grained regional descriptions and the models' insufficient ability to capture complex prompts. To address these limitations, we propose a Regional Attention Guided Super-Resolution (RAGSR) method that explicitly extracts localized fine-grained information and effectively encodes it through a novel regional attention mechanism, enabling both enhanced detail and overall visually coherent SR results. Specifically, RAGSR localizes object regions in an image and assigns fine-grained caption to each region, which are formatted as region-text pairs as textual priors for T2I models. A regional guided attention is then leveraged to ensure that each region-text pair is properly considered in the attention process while preventing unwanted interactions between unrelated region-text pairs. By leveraging this attention mechanism, our approach offers finer control over the integration of text and image information, thereby effectively overcoming limitations faced by traditional SISR techniques. Experimental results on benchmark datasets demonstrate that our approach exhibits superior performance in generating perceptually authentic visual details while maintaining contextual consistency compared to existing approaches.

Dongyang Jin, Ryan Xu, Jianhao Zeng et al.

Recently, autoregressive (AR) models have shown strong potential in image generation, offering better scalability and easier integration with unified multi-modal systems compared to diffusion-based methods. However, extending AR models to general image editing remains challenging due to weak and inefficient conditioning, often leading to poor instruction adherence and visual artifacts. To address this, we propose SCAR, a Semantic-Context-driven method for Autoregressive models. SCAR introduces two key components: Compressed Semantic Prefilling, which encodes high-level semantics into a compact and efficient prefix, and Semantic Alignment Guidance, which aligns the last visual hidden states with target semantics during autoregressive decoding to enhance instruction fidelity. Unlike decoding-stage injection methods, SCAR builds upon the flexibility and generality of vector-quantized-based prefilling while overcoming its semantic limitations and high cost. It generalizes across both next-token and next-set AR paradigms with minimal architectural changes. SCAR achieves superior visual fidelity and semantic alignment on both instruction editing and controllable generation benchmarks, outperforming prior AR-based methods while maintaining controllability. All code will be released.

Jianhao Zeng, Yancheng Bai, Ruidong Chen et al.

Video virtual try-on technology provides a cost-effective solution for creating marketing videos in fashion e-commerce. However, its practical adoption is hindered by two critical limitations. First, the reliance on a single garment image as input in current virtual try-on datasets limits the accurate capture of realistic texture details. Second, most existing methods focus solely on generating full-shot virtual try-on videos, neglecting the business's demand for videos that also provide detailed close-ups. To address these challenges, we introduce a high-resolution dataset for video-based virtual try-on. This dataset offers two key features. First, it provides more detailed information on the garments, which includes high-fidelity images with detailed close-ups and textual descriptions; Second, it uniquely includes full-shot and close-up try-on videos of real human models. Furthermore, accurately assessing consistency becomes significantly more critical for the close-up videos, which demand high-fidelity preservation of garment details. To facilitate such fine-grained evaluation, we propose a new garment consistency metric VGID (Video Garment Inception Distance) that quantifies the preservation of both texture and structure. Our experiments validate these contributions. We demonstrate that by utilizing the detailed images from our dataset, existing video generation models can extract and incorporate texture features, significantly enhancing the realism and detail fidelity of virtual try-on results. Furthermore, we conduct a comprehensive benchmark of recent models. The benchmark effectively identifies the texture and structural preservation problems among current methods.

Yancheng Bai, Huijuan Xu, Kate Saenko et al.

Activity detection is a fundamental problem in computer vision. Detecting activities of different temporal scales is particularly challenging. In this paper, we propose the contextual multi-scale region convolutional 3D network (CMS-RC3D) for activity detection. To deal with the inherent temporal scale variability of activity instances, the temporal feature pyramid is used to represent activities of different temporal scales. On each level of the temporal feature pyramid, an activity proposal detector and an activity classifier are learned to detect activities of specific temporal scales. Temporal contextual information is fused into activity classifiers for better recognition. More importantly, the entire model at all levels can be trained end-to-end. Our CMS-RC3D detector can deal with activities at all temporal scale ranges with only a single pass through the backbone network. We test our detector on two public activity detection benchmarks, THUMOS14 and ActivityNet. Extensive experiments show that the proposed CMS-RC3D detector outperforms state-of-the-art methods on THUMOS14 by a substantial margin and achieves comparable results on ActivityNet despite using a shallow feature extractor.

Yancheng Bai, Bernard Ghanem

Face detection is a fundamental problem in computer vision. It is still a challenging task in unconstrained conditions due to significant variations in scale, pose, expressions, and occlusion. In this paper, we propose a multi-branch fully convolutional network (MB-FCN) for face detection, which considers both efficiency and effectiveness in the design process. Our MB-FCN detector can deal with faces at all scale ranges with only a single pass through the backbone network. As such, our MB-FCN model saves computation and thus is more efficient, compared to previous methods that make multiple passes. For each branch, the specific skip connections of the convolutional feature maps at different layers are exploited to represent faces in specific scale ranges. Specifically, small faces can be represented with both shallow fine-grained and deep powerful coarse features. With this representation, superior improvement in performance is registered for the task of detecting small faces. We test our MB-FCN detector on two public face detection benchmarks, including FDDB and WIDER FACE. Extensive experiments show that our detector outperforms state-of-the-art methods on all these datasets in general and by a substantial margin on the most challenging among them (e.g. WIDER FACE Hard subset). Also, MB-FCN runs at 15 FPS on a GPU for images of size 640 x 480 with no assumption on the minimum detectable face size.