Yuki Endo

Yuki Endo

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through additional visual guidance (e.g., sketches and semantic masks) but require additional training with annotated images. In this paper, we propose a method for spatially controlling text-to-image generation without further training of diffusion models. Our method is based on the insight that the cross-attention maps reflect the positional relationship between words and pixels. Our aim is to control the attention maps according to given semantic masks and text prompts. To this end, we first explore a simple approach of directly swapping the cross-attention maps with constant maps computed from the semantic regions. Some prior works also allow training-free spatial control of text-to-image diffusion models by directly manipulating cross-attention maps. However, these approaches still suffer from misalignment to given masks because manipulated attention maps are far from actual ones learned by diffusion models. To address this issue, we propose masked-attention guidance, which can generate images more faithful to semantic masks via indirect control of attention to each word and pixel by manipulating noise images fed to diffusion models. Masked-attention guidance can be easily integrated into pre-trained off-the-shelf diffusion models (e.g., Stable Diffusion) and applied to the tasks of text-guided image editing. Experiments show that our method enables more accurate spatial control than baselines qualitatively and quantitatively.

Yuta Okuyama, Yuki Endo, Yoshihiro Kanamori

Pose and body shape editing in a human image has received increasing attention. However, current methods often struggle with dataset biases and deteriorate realism and the person's identity when users make large edits. We propose a one-shot approach that enables large edits with identity preservation. To enable large edits, we fit a 3D body model, project the input image onto the 3D model, and change the body's pose and shape. Because this initial textured body model has artifacts due to occlusion and the inaccurate body shape, the rendered image undergoes a diffusion-based refinement, in which strong noise destroys body structure and identity whereas insufficient noise does not help. We thus propose an iterative refinement with weak noise, applied first for the whole body and then for the face. We further enhance the realism by fine-tuning text embeddings via self-supervised learning. Our quantitative and qualitative evaluations demonstrate that our method outperforms other existing methods across various datasets.

Xingchao Yang, Takafumi Taketomi, Yuki Endo et al.

In this work, we introduce two types of makeup prior models to extend existing 3D face prior models: PCA-based and StyleGAN2-based priors. The PCA-based prior model is a linear model that is easy to construct and is computationally efficient. However, it retains only low-frequency information. Conversely, the StyleGAN2-based model can represent high-frequency information with relatively higher computational cost than the PCA-based model. Although there is a trade-off between the two models, both are applicable to 3D facial makeup estimation and related applications. By leveraging makeup prior models and designing a makeup consistency module, we effectively address the challenges that previous methods faced in robustly estimating makeup, particularly in the context of handling self-occluded faces. In experiments, we demonstrate that our approach reduces computational costs by several orders of magnitude, achieving speeds up to 180 times faster. In addition, by improving the accuracy of the estimated makeup, we confirm that our methods are highly advantageous for various 3D facial makeup applications such as 3D makeup face reconstruction, user-friendly makeup editing, makeup transfer, and interpolation.

Shun Masuda, Yuki Endo, Yoshihiro Kanamori

Compositing human figures into scene images has broad applications in areas such as entertainment and advertising. However, existing methods often cannot handle occlusion of the inserted person by foreground objects and unnaturally place the person in the frontmost layer. Moreover, they offer limited control over the inserted person's pose. To address these challenges, we propose two methods. Both allow explicit pose control via a 3D body model and leverage latent diffusion models to synthesize the person at a contextually appropriate depth, naturally handling occlusions without requiring occlusion masks. The first is a two-stage approach: the model first learns a depth map of the scene with the person through supervised learning, and then synthesizes the person accordingly. The second method learns occlusion implicitly and synthesizes the person directly from input data without explicit depth supervision. Quantitative and qualitative evaluations show that both methods outperform existing approaches by better preserving scene consistency while accurately reflecting occlusions and user-specified poses.

Kazuki Higo, Toshiki Kanai, Yuki Endo et al.

3D terrain models are essential in fields such as video game development and film production. Since surface color often correlates with terrain geometry, capturing this relationship is crucial to achieving realism. However, most existing methods generate either a heightmap or a texture, without sufficiently accounting for the inherent correlation. In this paper, we propose a method that jointly generates terrain heightmaps and textures using a latent diffusion model. First, we train the model in an unsupervised manner to randomly generate paired heightmaps and textures. Then, we perform supervised learning of an external adapter to enable user control via hand-drawn sketches. Experiments show that our approach allows intuitive terrain generation while preserving the correlation between heightmaps and textures.

Yuki Endo, Yoshihiro Kanamori

This paper tackles a challenging problem of generating photorealistic images from semantic layouts in few-shot scenarios where annotated training pairs are hardly available but pixel-wise annotation is quite costly. We present a training strategy that performs pseudo labeling of semantic masks using the StyleGAN prior. Our key idea is to construct a simple mapping between the StyleGAN feature and each semantic class from a few examples of semantic masks. With such mappings, we can generate an unlimited number of pseudo semantic masks from random noise to train an encoder for controlling a pre-trained StyleGAN generator. Although the pseudo semantic masks might be too coarse for previous approaches that require pixel-aligned masks, our framework can synthesize high-quality images from not only dense semantic masks but also sparse inputs such as landmarks and scribbles. Qualitative and quantitative results with various datasets demonstrate improvement over previous approaches with respect to layout fidelity and visual quality in as few as one- or five-shot settings.

Yoshihiro Kanamori, Yuki Endo

Relighting of human images has various applications in image synthesis. For relighting, we must infer albedo, shape, and illumination from a human portrait. Previous techniques rely on human faces for this inference, based on spherical harmonics (SH) lighting. However, because they often ignore light occlusion, inferred shapes are biased and relit images are unnaturally bright particularly at hollowed regions such as armpits, crotches, or garment wrinkles. This paper introduces the first attempt to infer light occlusion in the SH formulation directly. Based on supervised learning using convolutional neural networks (CNNs), we infer not only an albedo map, illumination but also a light transport map that encodes occlusion as nine SH coefficients per pixel. The main difficulty in this inference is the lack of training datasets compared to unlimited variations of human portraits. Surprisingly, geometric information including occlusion can be inferred plausibly even with a small dataset of synthesized human figures, by carefully preparing the dataset so that the CNNs can exploit the data coherency. Our method accomplishes more realistic relighting than the occlusion-ignored formulation.