Author name cluster

Ceyuan Yang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

2 author rows

ICLR Conference 2025 Conference Paper

3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting

Qihang Zhang
Yinghao Xu 0001
Chaoyang Wang 0001
Hsin-Ying Lee 0001
Gordon Wetzstein
Bolei Zhou
Ceyuan Yang

Scene image editing is crucial for entertainment, photography, and advertising design. Existing methods solely focus on either 2D individual object or 3D global scene editing. This results in a lack of a unified approach to effectively control and manipulate scenes at the 3D level with different levels of granularity. In this work, we propose 3DitScene, a novel and unified scene editing framework leveraging language-guided disentangled Gaussian Splatting that enables seamless editing from 2D to 3D, allowing precise control over scene composition and individual objects. We first incorporate 3D Gaussians that are refined through generative priors and optimization techniques. Language features from CLIP then introduce semantics into 3D geometry for object disentanglement. With the disentangled Gaussians, 3DitScene allows for manipulation at both the global and individual levels, revolutionizing creative expression and empowering control over scenes and objects. Experimental results demonstrate the effectiveness and versatility of 3DitScene in scene image editing.

Details

NeurIPS Conference 2025 Conference Paper

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

Shanchuan Lin
Ceyuan Yang
Hao He
Jianwen Jiang
Yuxi Ren
Xin Xia
Yang Zhao
Xuefeng Xiao

Existing large-scale video generation models are computationally intensive, preventing adoption in real-time and interactive applications. In this work, we propose autoregressive adversarial post-training (AAPT) to turn a pre-trained latent video diffusion model into a real-time, interactive, streaming video generator. Our model autoregressively generates a latent frame at a time using a single neural function evaluation (1NFE). The model can stream the result to the user in real time and receive interactive responses as control to generate the next latent frame. Unlike existing approaches, our method explores adversarial training as an effective paradigm for autoregressive generation. This allows us to design a more efficient architecture for one-step generation and to train the model in a student-forcing way to mitigate error accumulation. The adversarial approach also enables us to train the model for long-duration generation fully utilizing the KV cache. As a result, our 8B model achieves real-time, 24fps, nonstop, streaming video generation at 736x416 resolution on a single H100, or 1280x720 on 8xH100 up to a minute long (1440 frames).

PDF Details

ICLR Conference 2025 Conference Paper

CameraCtrl: Enabling Camera Control for Video Diffusion Models

Hao He
Yinghao Xu 0001
Yuwei Guo 0002
Gordon Wetzstein
Bo Dai 0002
Hongsheng Li 0001
Ceyuan Yang

Controllability plays a crucial role in video generation, as it allows users to create and edit content more precisely. Existing models, however, lack control of camera pose that serves as a cinematic language to express deeper narrative nuances. To alleviate this issue, we introduce \method, enabling accurate camera pose control for video diffusion models. Our approach explores effective camera trajectory parameterization along with a plug-and-play camera pose control module that is trained on top of a video diffusion model, leaving other modules of the base model untouched. Moreover, a comprehensive study on the effect of various training datasets is conducted, suggesting that videos with diverse camera distributions and similar appearance to the base model indeed enhance controllability and generalization. Experimental results demonstrate the effectiveness of \method in achieving precise camera control with different video generation models, marking a step forward in the pursuit of dynamic and customized video storytelling from textual and camera pose inputs.

Details

ICML Conference 2025 Conference Paper

Diffusion Adversarial Post-Training for One-Step Video Generation

Shanchuan Lin
Xin Xia 0014
Yuxi Ren
Ceyuan Yang
Xuefeng Xiao 0001
Lu Jiang

The diffusion models are widely used for image and video generation, but their iterative generation process is slow and expansive. While existing distillation approaches have demonstrated the potential for one-step generation in the image domain, they still suffer from significant quality degradation. In this work, we propose Adversarial Post-Training (APT) against real data following diffusion pre-training for one-step video generation. To improve the training stability and quality, we introduce several improvements to the model architecture and training procedures, along with an approximated R1 regularization objective. Empirically, our experiments show that our adversarial post-trained model can generate two-second, 1280x720, 24fps videos in real-time using a single forward evaluation step. Additionally, our model is capable of generating 1024px images in a single step, achieving quality comparable to state-of-the-art methods.

Details

ICML Conference 2025 Conference Paper

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

Qin Guo
Ailing Zeng
Dongxu Yue
Ceyuan Yang
Yang Cao 0017
Hanzhong Guo
Fei Shen
Wei Liu 0005

Although significant advancements have been achieved in the progress of keypoint-guided Text-to-Image diffusion models, existing mainstream keypoint-guided models encounter challenges in controlling the generation of more general non-rigid objects beyond humans (e. g. , animals). Moreover, it is difficult to generate multiple overlapping humans and animals based on keypoint controls solely. These challenges arise from two main aspects: the inherent limitations of existing controllable methods and the lack of suitable datasets. First, we design a DiT-based framework, named UniMC, to explore unifying controllable multi-class image generation. UniMC integrates instance- and keypoint-level conditions into compact tokens, incorporating attributes such as class, bounding box, and keypoint coordinates. This approach overcomes the limitations of previous methods that struggled to distinguish instances and classes due to their reliance on skeleton images as conditions. Second, we propose HAIG-2. 9M, a large-scale, high-quality, and diverse dataset designed for keypoint-guided human and animal image generation. HAIG-2. 9M includes 786K images with 2. 9M instances. This dataset features extensive annotations such as keypoints, bounding boxes, and fine-grained captions for both humans and animals, along with rigorous manual inspection to ensure annotation accuracy. Extensive experiments demonstrate the high quality of HAIG-2. 9M and the effectiveness of UniMC, particularly in heavy occlusions and multi-class scenarios.

Details

ICLR Conference 2024 Conference Paper

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

Yuwei Guo 0002
Ceyuan Yang
Anyi Rao
Zhengyang Liang
Yaohui Wang 0001
Yu Qiao 0001
Maneesh Agrawala
Dahua Lin

With the advance of text-to-image (T2I) diffusion models (e.g., Stable Diffusion) and corresponding personalization techniques such as DreamBooth and LoRA, everyone can manifest their imagination into high-quality images at an affordable cost. However, adding motion dynamics to existing high-quality personalized T2Is and enabling them to generate animations remains an open challenge. In this paper, we present AnimateDiff, a practical framework for animating personalized T2I models without requiring model-specific tuning. At the core of our framework is a plug-and-play motion module that can be trained once and seamlessly integrated into any personalized T2Is originating from the same base T2I. Through our proposed training strategy, the motion module effectively learns transferable motion priors from real-world videos. Once trained, the motion module can be inserted into a personalized T2I model to form a personalized animation generator. We further propose MotionLoRA, a lightweight fine-tuning technique for AnimateDiff that enables a pre-trained motion module to adapt to new motion patterns, such as different shot types, at a low training and data collection cost. We evaluate AnimateDiff and MotionLoRA on several public representative personalized T2I models collected from the community. The results demonstrate that our approaches help these models generate temporally smooth animation clips while preserving the visual quality and motion diversity. Codes and pre-trained weights are available at https://github.com/guoyww/AnimateDiff.

Details

ICML Conference 2024 Conference Paper

SMaRt: Improving GANs with Score Matching Regularity

Mengfei Xia
Yujun Shen
Ceyuan Yang
Ran Yi 0002
Wenping Wang 0001
Yong-Jin Liu 0001

Generative adversarial networks (GANs) usually struggle in learning from highly diverse data, whose underlying manifold is complex. In this work, we revisit the mathematical foundations of GANs, and theoretically reveal that the native adversarial loss for GAN training is insufficient to fix the problem of $\textit{subsets with positive Lebesgue measure of the generated data manifold lying out of the real data manifold}$. Instead, we find that score matching serves as a promising solution to this issue thanks to its capability of persistently pushing the generated data points towards the real data manifold. We thereby propose to improve the optimization of GANs with score matching regularity (SMaRt). Regarding the empirical evidences, we first design a toy example to show that training GANs by the aid of a ground-truth score function can help reproduce the real data distribution more accurately, and then confirm that our approach can consistently boost the synthesis performance of various state-of-the-art GANs on real-world datasets with pre-trained diffusion models acting as the approximate score function. For instance, when training Aurora on the ImageNet $64\times64$ dataset, we manage to improve FID from 8. 87 to 7. 11, on par with the performance of one-step consistency model. Code is available at https: //github. com/thuxmf/SMaRt.

Details

NeurIPS Conference 2023 Conference Paper

Learning Modulated Transformation in GANs

Ceyuan Yang
Qihang Zhang
Yinghao Xu
Jiapeng Zhu
Yujun Shen
Bo Dai

The success of style-based generators largely benefits from style modulation, which helps take care of the cross-instance variation within data. However, theinstance-wise stochasticity is typically introduced via regular convolution, wherekernels interact with features at some fixed locations, limiting its capacity formodeling geometric variation. To alleviate this problem, we equip the generatorin generative adversarial networks (GANs) with a plug-and-play module, termedas modulated transformation module (MTM). This module predicts spatial offsetsunder the control of latent codes, based on which the convolution operation canbe applied at variable locations for different instances, and hence offers the modelan additional degree of freedom to handle geometry deformation. Extensiveexperiments suggest that our approach can be faithfully generalized to variousgenerative tasks, including image generation, 3D-aware image synthesis, andvideo generation, and get compatible with state-of-the-art frameworks withoutany hyper-parameter tuning. It is noteworthy that, towards human generation onthe challenging TaiChi dataset, we improve the FID of StyleGAN3 from 21. 36 to13. 60, demonstrating the efficacy of learning modulated geometry transformation. Code and models are available at https: //github. com/limbo0000/mtm.

PDF Details

NeurIPS Conference 2023 Conference Paper

Revisiting the Evaluation of Image Synthesis with GANs

Mengping Yang
Ceyuan Yang
Yichi Zhang
Qingyan Bai
Yujun Shen
Bo Dai

A good metric, which promises a reliable comparison between solutions, is essential for any well-defined task. Unlike most vision tasks that have per-sample ground-truth, image synthesis tasks target generating unseen data and hence are usually evaluated through a distributional distance between one set of real samples and another set of generated samples. This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set. Extensive experiments conducted on multiple datasets and settings reveal several important findings. Firstly, a group of models that include both CNN-based and ViT-based architectures serve as reliable and robust feature extractors for measurement evaluation. Secondly, Centered Kernel Alignment (CKA) provides a better comparison across various extractors and hierarchical layers in one model. Finally, CKA is more sample-efficient and enjoys better agreement with human judgment in characterizing the similarity between two internal data correlations. These findings contribute to the development of a new measurement system, which enables a consistent and reliable re-evaluation of current state-of-the-art generative models.

PDF Details

ICLR Conference 2023 Conference Paper

Towards Smooth Video Composition

Qihang Zhang
Ceyuan Yang
Yujun Shen
Yinghao Xu 0001
Bolei Zhou

Video generation, with the purpose of producing a sequence of frames, requires synthesizing consistent and persistent dynamic contents over time. This work investigates how to model the temporal relations for composing a video with arbitrary number of frames, from a few to even infinite, using generative adversarial networks (GANs). First, towards composing adjacent frames, we show that the alias-free operation for single image generation, together with adequately pre-learned knowledge, bring a smooth frame transition without harming the per-frame quality. Second, through incorporating a temporal shift module (TSM), which is originally designed for video understanding, into the discriminator, we manage to advance the generator in synthesizing more reasonable dynamics. Third, we develop a novel B-Spline based motion representation to ensure the temporal smoothness, and hence achieve infinite-length video generation, going beyond the frame number used in training. We evaluate our approach on a range of datasets and show substantial improvements over baselines on video generation. Code and models are publicly available at \url{https://genforce.github.io/StyleSV}.

Details

NeurIPS Conference 2022 Conference Paper

Improving GANs with A Dynamic Discriminator

Ceyuan Yang
Yujun Shen
Yinghao Xu
Deli Zhao
Bo Dai
Bolei Zhou

Discriminator plays a vital role in training generative adversarial networks (GANs) via distinguishing real and synthesized samples. While the real data distribution remains the same, the synthesis distribution keeps varying because of the evolving generator, and thus effects a corresponding change of the bi-classification task assigned to the discriminator. We argue that a discriminator with an on-the-fly adjustment on its capacity can better accommodate such a time-varying task. A comprehensive empirical study confirms that the proposed training strategy, termed as DynamicD, improves the synthesis performance without incurring any additional computation cost or training objectives. Two capacity adjusting schemes are developed for training GANs under different data regimes: i) given a sufficient amount of training data, the discriminator benefits from a progressively increased learning capacity, and ii) when the training data is limited, gradually decreasing the layer width mitigates the over-fitting issue of the discriminator. Experiments on both 2D and 3D-aware image synthesis tasks conducted on a range of datasets substantiate the generalizability of our DynamicD as well as its substantial improvement over the baselines. Furthermore, DynamicD is synergistic to other discriminator-improving approaches (including data augmentation, regularizers, and pre-training), and brings continuous performance gain when combined with them for learning GANs. Code will be made publicly available.

PDF Details

NeurIPS Conference 2021 Conference Paper

Data-Efficient Instance Generation from Instance Discrimination

Ceyuan Yang
Yujun Shen
Yinghao Xu
Bolei Zhou

Generative Adversarial Networks (GANs) have significantly advanced image synthesis, however, the synthesis quality drops significantly given a limited amount of training data. To improve the data efficiency of GAN training, prior work typically employs data augmentation to mitigate the overfitting of the discriminator yet still learn the discriminator with a bi-classification ($\textit{i. e. }$, real $\textit{vs. }$ fake) task. In this work, we propose a data-efficient Instance Generation ($\textit{InsGen}$) method based on instance discrimination. Concretely, besides differentiating the real domain from the fake domain, the discriminator is required to distinguish every individual image, no matter it comes from the training set or from the generator. In this way, the discriminator can benefit from the infinite synthesized samples for training, alleviating the overfitting problem caused by insufficient training data. A noise perturbation strategy is further introduced to improve its discriminative power. Meanwhile, the learned instance discrimination capability from the discriminator is in turn exploited to encourage the generator for diverse generation. Extensive experiments demonstrate the effectiveness of our method on a variety of datasets and training settings. Noticeably, on the setting of $2K$ training images from the FFHQ dataset, we outperform the state-of-the-art approach with 23. 5\% FID improvement.

PDF Details