arXiv subjects

Dohae Lee

Publications and source records attributed to Dohae Lee.

5 recordsLinked to original sources

arXiv2023

Semantic Guidance Tuning for Text-To-Image Diffusion Models

Recent advancements in Text-to-Image (T2I) diffusion models have demonstrated impressive success in generating high-quality images with zero-shot generalization capabilities. Yet, current models struggle to closely adhere to prompt semantics, often misrepresenting or overlooking specific attributes. To address this, we propose a simple, training-free approach that modulates the guidance direction of diffusion models during inference. We first decompose the prompt semantics into a set of concepts, and monitor the guidance trajectory in relation to each concept. Our key observation is that deviations in model's adherence to prompt semantics are highly correlated with divergence of the guidance from one or more of these concepts. Based on this observation, we devise a technique to steer the guidance direction towards any concept from which the model diverges. Extensive experimentation validates that our method improves the semantic alignment of images generated by diffusion models in response to prompts. Project page is available at: https://korguy.github.io/

cs.CV↗

arXiv2023

Utilizing Task-Generic Motion Prior to Recover Full-Body Motion from Very Sparse Signals

The most popular type of devices used to track a user's posture in a virtual reality experience consists of a head-mounted display and two controllers held in both hands. However, due to the limited number of tracking sensors (three in total), faithfully recovering the user in full-body is challenging, limiting the potential for interactions among simulated user avatars within the virtual world. Therefore, recent studies have attempted to reconstruct full-body poses using neural networks that utilize previously learned human poses or accept a series of past poses over a short period. In this paper, we propose a method that utilizes information from a neural motion prior to improve the accuracy of reconstructed user's motions. Our approach aims to reconstruct user's full-body poses by predicting the latent representation of the user's overall motion from limited input signals and integrating this information with tracking sensor inputs. This is based on the premise that the ultimate goal of pose reconstruction is to reconstruct the motion, which is a series of poses. Our results show that this integration enables more accurate reconstruction of the user's full-body motion, particularly enhancing the robustness of lower body motion reconstruction from impoverished signals. Web: https://https://mjsh34.github.io/mp-sspe/

cs.CV↗

arXiv2023

ClothCombo: Modeling Inter-Cloth Interaction for Draping Multi-Layered Clothes

We present ClothCombo, a pipeline to drape arbitrary combinations of clothes on 3D human models with varying body shapes and poses. While existing learning-based approaches for draping clothes have shown promising results, multi-layered clothing remains challenging as it is non-trivial to model inter-cloth interaction. To this end, our method utilizes a GNN-based network to efficiently model the interaction between clothes in different layers, thus enabling multi-layered clothing. Specifically, we first create feature embedding for each cloth using a topology-agnostic network. Then, the draping network deforms all clothes to fit the target body shape and pose without considering inter-cloth interaction. Lastly, the untangling network predicts the per-vertex displacements in a way that resolves interpenetration between clothes. In experiments, the proposed model demonstrates strong performance in complex multi-layered scenarios. Being agnostic to cloth topology, our method can be readily used for layered virtual try-on of real clothes in diverse poses and combinations of clothes.

cs.CV↗

arXiv2022

CIMS: Correction-Interpolation Method for Smoke Simulation

In this paper, we propose CIMS: a novel correction-interpolation method for smoke simulation. The basis of our method is to first generate a low frame rate smoke simulation, then increase the frame rate using temporal interpolation. However, low frame rate smoke simulations are inaccurate as they require increasing the time-step. A simulation with a larger time-step produces results different from that of the original simulation with a small time-step. Therefore, the proposed method corrects the large time-step simulation results closer to the corresponding small time-step simulation results using a U-Net-based DNN model. To obtain more precise results, we applied modeling concepts used in the image domain, such as optical flow and perceptual loss. By correcting the large time-step simulation results and interpolating between them, the proposed method can efficiently and accurately generate high frame rate smoke simulations. We conduct qualitative and quantitative analyses to confirm the effectiveness of the proposed model. Our analyses show that our method reduces the mean squared error of large time-step simulation results by more than 80% on average. Our method also produces results closer to the ground truth than the previous DNN-based methods; it is on average 2.04 times more accurate than previous works. In addition, the computation time of the proposed correction method barely affects the overall computation time.

cs.GR↗

arXiv2021

Discovering Latent Representations of Relations for Interacting Systems

Systems whose entities interact with each other are common. In many interacting systems, it is difficult to observe the relations between entities which is the key information for analyzing the system. In recent years, there has been increasing interest in discovering the relationships between entities using graph neural networks. However, existing approaches are difficult to apply if the number of relations is unknown or if the relations are complex. We propose the DiScovering Latent Relation (DSLR) model, which is flexibly applicable even if the number of relations is unknown or many types of relations exist. The flexibility of our DSLR model comes from the design concept of our encoder that represents the relation between entities in a latent space rather than a discrete variable and a decoder that can handle many types of relations. We performed the experiments on synthetic and real-world graph data with various relationships between entities, and compared the qualitative and quantitative results with other approaches. The experiments show that the proposed method is suitable for analyzing dynamic graphs with an unknown number of complex relations.

cs.AI↗