Jinlin Liu

Mengyang Feng, Jinlin Liu, Miaomiao Cui et al.

This is a technical report on the 360-degree panoramic image generation task based on diffusion models. Unlike ordinary 2D images, 360-degree panoramic images capture the entire $360^\circ\times 180^\circ$ field of view. So the rightmost and the leftmost sides of the 360 panoramic image should be continued, which is the main challenge in this field. However, the current diffusion pipeline is not appropriate for generating such a seamless 360-degree panoramic image. To this end, we propose a circular blending strategy on both the denoising and VAE decoding stages to maintain the geometry continuity. Based on this, we present two models for \textbf{Text-to-360-panoramas} and \textbf{Single-Image-to-360-panoramas} tasks. The code has been released as an open-source project at \href{https://github.com/ArcherFMY/SD-T2I-360PanoImage}{https://github.com/ArcherFMY/SD-T2I-360PanoImage} and \href{https://www.modelscope.cn/models/damo/cv_diffusion_text-to-360panorama-image_generation/summary}{ModelScope}

Xiefan Guo, Jinlin Liu, Miaomiao Cui et al.

Recent strides in the development of diffusion models, exemplified by advancements such as Stable Diffusion, have underscored their remarkable prowess in generating visually compelling images. However, the imperative of achieving a seamless alignment between the generated image and the provided prompt persists as a formidable challenge. This paper traces the root of these difficulties to invalid initial noise, and proposes a solution in the form of Initial Noise Optimization (InitNO), a paradigm that refines this noise. Considering text prompts, not all random noises are effective in synthesizing semantically-faithful images. We design the cross-attention response score and the self-attention conflict score to evaluate the initial noise, bifurcating the initial latent space into valid and invalid sectors. A strategically crafted noise optimization pipeline is developed to guide the initial noise towards valid regions. Our method, validated through rigorous experimentation, shows a commendable proficiency in generating images in strict accordance with text prompts. Our code is available at https://github.com/xiefan-guo/initno.

Kai Yu, Jinlin Liu, Mengyang Feng et al.

We present Boosting3D, a multi-stage single image-to-3D generation method that can robustly generate reasonable 3D objects in different data domains. The point of this work is to solve the view consistency problem in single image-guided 3D generation by modeling a reasonable geometric structure. For this purpose, we propose to utilize better 3D prior to training the NeRF. More specifically, we train an object-level LoRA for the target object using original image and the rendering output of NeRF. And then we train the LoRA and NeRF using a progressive training strategy. The LoRA and NeRF will boost each other while training. After the progressive training, the LoRA learns the 3D information of the generated object and eventually turns to an object-level 3D prior. In the final stage, we extract the mesh from the trained NeRF and use the trained LoRA to optimize the structure and appearance of the mesh. The experiments demonstrate the effectiveness of the proposed method. Boosting3D learns object-specific 3D prior which is beyond the ability of pre-trained diffusion priors and achieves state-of-the-art performance in the single image-to-3d generation task.

Haitao Zhou, Chuang Wang, Rui Nie et al.

Recent years have seen substantial progress in diffusion-based controllable video generation. However, achieving precise control in complex scenarios, including fine-grained object parts, sophisticated motion trajectories, and coherent background movement, remains a challenge. In this paper, we introduce TrackGo, a novel approach that leverages free-form masks and arrows for conditional video generation. This method offers users with a flexible and precise mechanism for manipulating video content. We also propose the TrackAdapter for control implementation, an efficient and lightweight adapter designed to be seamlessly integrated into the temporal self-attention layers of a pretrained video generation model. This design leverages our observation that the attention map of these layers can accurately activate regions corresponding to motion in videos. Our experimental results demonstrate that our new approach, enhanced by the TrackAdapter, achieves state-of-the-art performance on key metrics such as FVD, FID, and ObjMC scores.

Jinlin Liu

Due to the difficulty of solving the matting problem, lots of methods use some kinds of assistance to acquire high quality alpha matte. Green screen matting methods rely on physical equipment. Trimap-based methods take manual interactions as external input. Background-based methods require a pre-captured, static background. The methods are not flexible and convenient enough to use widely. Trimap-free methods are flexible but not stable in complicated video applications. To be stable and flexible in real applications, we propose an adaptive background matting method. The user first captures their videos freely, moving the cameras. Then the user captures the background video afterwards, roughly covering the previous captured regions. We use dynamic background video instead of static background for accurate matting. The proposed method is convenient to use in any scenes as the static camera and background is no more the limitation. To achieve this goal, we use background matching network to find the best-matched background frame by frame from dynamic backgrounds. Then, robust semantic estimation network is used to estimate the coarse alpha matte. Finally, we crop and zoom the target region according to the coarse alpha matte, and estimate the final accurate alpha matte. In experiments, the proposed method is able to perform comparably against the state-of-the-art matting methods.

Zhaoqing Wang, Xiaobo Xia, Zhuolin Bie et al.

Recent advances in video diffusion models have remarkably improved camera-controlled video generation, but most methods rely solely on supervised fine-tuning (SFT), leaving online reinforcement learning (RL) post-training largely underexplored. In this work, we introduce an online RL post-training framework that optimizes a pretrained video generator for precise camera control. To make RL effective in this setting, we design a verifiable geometry reward that delivers dense segment-level feedback to guide model optimization. Specifically, we estimate the 3D camera trajectories for both generated and reference videos, divide each trajectory into short segments, and compute segment-wise relative poses. The reward function then compares each generated-reference segment pair and assigns an alignment score as the reward signal, which helps alleviate reward sparsity and improve optimization efficiency. Moreover, we construct a comprehensive dataset featuring diverse large-amplitude camera motions and scenes with varied subject dynamics. Extensive experiments show that our online RL post-training clearly outperforms SFT baselines across multiple aspects, including camera-control accuracy, geometric consistency, and visual quality, demonstrating its superiority in advancing camera-controlled video generation.

Mengyang Feng, Jinlin Liu, Kai Yu et al.

In this paper, we present DreaMoving, a diffusion-based controllable video generation framework to produce high-quality customized human videos. Specifically, given target identity and posture sequences, DreaMoving can generate a video of the target identity moving or dancing anywhere driven by the posture sequences. To this end, we propose a Video ControlNet for motion-controlling and a Content Guider for identity preserving. The proposed model is easy to use and can be adapted to most stylized diffusion models to generate diverse results. The project page is available at https://dreamoving.github.io/dreamoving

Jinlin Liu, Wei Chen, Xiaojin Zhang

Collecting web data to train deep models has become increasingly common, raising concerns about unauthorized data usage. To mitigate this issue, unlearnable examples introduce imperceptible perturbations into data, preventing models from learning effectively. However, existing methods typically rely on deep neural networks as surrogate models for perturbation generation, resulting in significant computational costs. In this work, we propose Perturbation-Induced Linearization (PIL), a computationally efficient yet effective method that generates perturbations using only linear surrogate models. PIL achieves comparable or better performance than existing surrogate-based methods while reducing computational time dramatically. We further reveal a key mechanism underlying unlearnable examples: inducing linearization to deep models, which explains why PIL can achieve competitive results in a very short time. Beyond this, we provide an analysis about the property of unlearnable examples under percentage-based partial perturbation. Our work not only provides a practical approach for data protection but also offers insights into what makes unlearnable examples effective.

Xiefan Guo, Jinlin Liu, Miaomiao Cui et al.

Text-to-video generation has trailed behind text-to-image generation in terms of quality and diversity, primarily due to the inherent complexities of spatio-temporal modeling and the limited availability of video-text datasets. Recent text-to-video diffusion models employ the image as an intermediate step, significantly enhancing overall performance but incurring high training costs. In this paper, we present I4VGen, a novel video diffusion inference pipeline to leverage advanced image techniques to enhance pre-trained text-to-video diffusion models, which requires no additional training. Instead of the vanilla text-to-video inference pipeline, I4VGen consists of two stages: anchor image synthesis and anchor image-augmented text-to-video synthesis. Correspondingly, a simple yet effective generation-selection strategy is employed to achieve visually-realistic and semantically-faithful anchor image, and an innovative noise-invariant video score distillation sampling (NI-VSDS) is developed to animate the image to a dynamic video by distilling motion knowledge from video diffusion models, followed by a video regeneration process to refine the video. Extensive experiments show that the proposed method produces videos with higher visual realism and textual fidelity. Furthermore, I4VGen also supports being seamlessly integrated into existing image-to-video diffusion models, thereby improving overall video quality.

Jinlin Liu, Yuan Yao, Wendi Hou et al.

Semantic human matting aims to estimate the per-pixel opacity of the foreground human regions. It is quite challenging and usually requires user interactive trimaps and plenty of high quality annotated data. Annotating such kind of data is labor intensive and requires great skills beyond normal users, especially considering the very detailed hair part of humans. In contrast, coarse annotated human dataset is much easier to acquire and collect from the public dataset. In this paper, we propose to use coarse annotated data coupled with fine annotated data to boost end-to-end semantic human matting without trimaps as extra input. Specifically, we train a mask prediction network to estimate the coarse semantic mask using the hybrid data, and then propose a quality unification network to unify the quality of the previous coarse mask outputs. A matting refinement network takes in the unified mask and the input image to predict the final alpha matte. The collected coarse annotated dataset enriches our dataset significantly, allows generating high quality alpha matte for real images. Experimental results show that the proposed method performs comparably against state-of-the-art methods. Moreover, the proposed method can be used for refining coarse annotated public dataset, as well as semantic segmentation methods, which reduces the cost of annotating high quality human data to a great extent.

Jinlin Liu, Yuan Yao, Jianqiang Ren

Synthesis of high resolution images using Generative Adversarial Networks (GANs) is challenging, which usually requires numbers of high-end graphic cards with large memory and long time of training. In this paper, we propose a two-stage framework to accelerate the training process of synthesizing high resolution images. High resolution images are first transformed to small codes via the trained encoder and decoder networks. The code in latent space is times smaller than the original high resolution images. Then, we train a code generation network to learn the distribution of the latent codes. In this way, the generator only learns to generate small latent codes instead of large images. Finally, we decode the generated latent codes to image space via the decoder networks so as to output the synthesized high resolution images. Experimental results show that the proposed method accelerates the training process significantly and increases the quality of the generated samples. The proposed acceleration framework makes it possible to generate high resolution images using less training time with limited hardware resource. After using the proposed acceleration method, it takes only 3 days to train a 1024 *1024 image generator on Celeba-HQ dataset using just one NVIDIA P100 graphic card.

Jiahui Qiu, Yangming Zhou, Zhiyuan Ma et al.

Clinical text structuring is a critical and fundamental task for clinical research. Traditional methods such as taskspecific end-to-end models and pipeline models usually suffer from the lack of dataset and error propagation. In this paper, we present a question answering based clinical text structuring (QA-CTS) task to unify different specific tasks and make dataset shareable. A novel model that aims to introduce domain-specific features (e.g., clinical named entity information) into pre-trained language model is also proposed for QA-CTS task. Experimental results on Chinese pathology reports collected from Ruijing Hospital demonstrate our presented QA-CTS task is very effective to improve the performance on specific tasks. Our proposed model also competes favorably with strong baseline models in specific tasks.