The development of text-to-video (T2V), i.e., generating videos with a given text prompt, has been significantly advanced in recent years. However, relying solely on text prompts often results in ambiguous frame composition due to spatial uncertainty. The research community thus leverages the dense structure signals, e.g., per-frame depth/edge sequences, to enhance controllability, whose collection accordingly increases the burden of inference. In this work, we present SparseCtrl to enable flexible structure control with temporally sparse signals, requiring only one or a few inputs, as shown in Figure 1. It incorporates an additional condition encoder to process these sparse signals while leaving the pre-trained T2V model untouched. The proposed approach is compatible with various modalities, including sketches, depth maps, and RGB images, providing more practical control for video generation and promoting applications such as storyboarding, depth rendering, keyframe animation, and interpolation. Extensive experiments demonstrate the generalization of SparseCtrl on both original and personalized T2V generators. Codes and models will be publicly available at https://guoyww.github.io/projects/SparseCtrl .
Text-conditioned human motion generation model has achieved great progress by introducing diffusion models and corresponding control signals. However, the interaction between humans are still under explored. To model interactions of arbitrary number of humans, we define interactions as human joint pairs that are either in contact or separated, and leverage {\em Large Language Model (LLM) Planner} to translate interaction descriptions into contact plans. Based on the contact plans, interaction generation could be achieved by spatially controllable motion generation methods by taking joint contacts as spatial conditions. We present a novel approach named InterControl for flexible spatial control of every joint in every person at any time by leveraging motion diffusion model only trained on single-person data. We incorporate a motion controlnet to generate coherent and realistic motions given sparse spatial control signals and a loss guidance module to precisely align any joint to the desired position in a classifier guidance manner via Inverse Kinematics (IK). Extensive experiments on HumanML3D and KIT-ML dataset demonstrate its effectiveness in versatile joint control. We also collect data of joint contact pairs by LLMs to show InterControl's ability in human interaction generation.
Pre-training a model and then fine-tuning it on downstream tasks has demonstrated significant success in the 2D image and NLP domains. However, due to the unordered and non-uniform density characteristics of point clouds, it is non-trivial to explore the prior knowledge of point clouds and pre-train a point cloud backbone. In this paper, we propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif). We consider the point cloud pre-training task as a conditional point-to-point generation problem and introduce a conditional point generator. This generator aggregates the features extracted by the backbone and employs them as the condition to guide the point-to-point recovery from the noisy point cloud, thereby assisting the backbone in capturing both local and global geometric priors as well as the global point density distribution of the object. We also present a recurrent uniform sampling optimization strategy, which enables the model to uniformly recover from various noise levels and learn from balanced supervision. Our PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection. Specifically, PointDif attains 70.0% mIoU on S3DIS Area 5 for the segmentation task and achieves an average improvement of 2.4% on ScanObjectNN for the classification task compared to TAP. Furthermore, our pre-training framework can be flexibly applied to diverse point cloud backbones and bring considerable gains.
In real-world reinforcement learning problems, the state information is often only partially observable, which breaks the basic assumption in Markov decision processes, and thus, leads to inferior performances. Partially Observable Markov Decision Processes have been introduced to explicitly take the issue into account for learning, exploration, and planning, but presenting significant computational and statistical challenges. To address these difficulties, we exploit the representation view, which leads to a coherent design framework for a practically tractable reinforcement learning algorithm upon partial observations. We provide a theoretical analysis for justifying the statistical efficiency of the proposed algorithm. We also empirically demonstrate the proposed algorithm can surpass state-of-the-art performance with partial observations across various benchmarks, therefore, pushing reliable reinforcement learning towards more practical applications.
Visually-rich document entity retrieval (VDER), which extracts key information (e.g. date, address) from document images like invoices and receipts, has become an important topic in industrial NLP applications. The emergence of new document types at a constant pace, each with its unique entity types, presents a unique challenge: many documents contain unseen entity types that occur only a couple of times. Addressing this challenge requires models to have the ability of learning entities in a few-shot manner. However, prior works for Few-shot VDER mainly address the problem at the document level with a predefined global entity space, which doesn't account for the entity-level few-shot scenario: target entity types are locally personalized by each task and entity occurrences vary significantly among documents. To address this unexplored scenario, this paper studies a novel entity-level few-shot VDER task. The challenges lie in the uniqueness of the label space for each task and the increased complexity of out-of-distribution (OOD) contents. To tackle this novel task, we present a task-aware meta-learning based framework, with a central focus on achieving effective task personalization that distinguishes between in-task and out-of-task distribution. Specifically, we adopt a hierarchical decoder (HC) and employ contrastive learning (ContrastProtoNet) to achieve this goal. Furthermore, we introduce a new dataset, FewVEX, to boost future research in the field of entity-level few-shot VDER. Experimental results demonstrate our approaches significantly improve the robustness of popular meta-learning baselines.
Neural radiance fields (NeRF) and its subsequent variants have led to remarkable progress in neural rendering. While most of recent neural rendering works focus on objects and small-scale scenes, developing neural rendering methods for city-scale scenes is of great potential in many real-world applications. However, this line of research is impeded by the absence of a comprehensive and high-quality dataset, yet collecting such a dataset over real city-scale scenes is costly, sensitive, and technically difficult. To this end, we build a large-scale, comprehensive, and high-quality synthetic dataset for city-scale neural rendering researches. Leveraging the Unreal Engine 5 City Sample project, we develop a pipeline to easily collect aerial and street city views, accompanied by ground-truth camera poses and a range of additional data modalities. Flexible controls over environmental factors like light, weather, human and car crowd are also available in our pipeline, supporting the need of various tasks covering city-scale neural rendering and beyond. The resulting pilot dataset, MatrixCity, contains 67k aerial images and 452k street images from two city maps of total size $28km^2$. On top of MatrixCity, a thorough benchmark is also conducted, which not only reveals unique challenges of the task of city-scale neural rendering, but also highlights potential improvements for future works. The dataset and code will be publicly available at our project page: https://city-super.github.io/matrixcity/.
We present a new method for generating realistic and view-consistent images with fine geometry from 2D image collections. Our method proposes a hybrid explicit-implicit representation called \textbf{OrthoPlanes}, which encodes fine-grained 3D information in feature maps that can be efficiently generated by modifying 2D StyleGANs. Compared to previous representations, our method has better scalability and expressiveness with clear and explicit information. As a result, our method can handle more challenging view-angles and synthesize articulated objects with high spatial degree of freedom. Experiments demonstrate that our method achieves state-of-the-art results on FFHQ and SHHQ datasets, both quantitatively and qualitatively. Project page: \url{https://orthoplanes.github.io/}.
This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of visually realistic and temporally coherent videos while b) preserving the strong creative generation nature of the pre-trained T2I model. To this end, we propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model. Our key insights are two-fold: 1) We reveal that the incorporation of simple temporal self-attentions, coupled with rotary positional encoding, adequately captures the temporal correlations inherent in video data. 2) Additionally, we validate that the process of joint image-video fine-tuning plays a pivotal role in producing high-quality and creative outcomes. To enhance the performance of LaVie, we contribute a comprehensive and diverse video dataset named Vimeo25M, consisting of 25 million text-video pairs that prioritize quality, diversity, and aesthetic appeal. Extensive experiments demonstrate that LaVie achieves state-of-the-art performance both quantitatively and qualitatively. Furthermore, we showcase the versatility of pre-trained LaVie models in various long video generation and personalized video synthesis applications.
There has been a debate about the superiority between vision Transformers and ConvNets, serving as the backbone of computer vision models. Although they are usually considered as two completely different architectures, in this paper, we interpret vision Transformers as ConvNets with dynamic convolutions, which enables us to characterize existing Transformers and dynamic ConvNets in a unified framework and compare their design choices side by side. In addition, our interpretation can also guide the network design as researchers now can consider vision Transformers from the design space of ConvNets and vice versa. We demonstrate such potential through two specific studies. First, we inspect the role of softmax in vision Transformers as the activation function and find it can be replaced by commonly used ConvNets modules, such as ReLU and Layer Normalization, which results in a faster convergence rate and better performance. Second, following the design of depth-wise convolution, we create a corresponding depth-wise vision Transformer that is more efficient with comparable performance. The potential of the proposed unified interpretation is not limited to the given examples and we hope it can inspire the community and give rise to more advanced network architectures.
Human-Scene Interaction (HSI) is a vital component of fields like embodied AI and virtual reality. Despite advancements in motion quality and physical plausibility, two pivotal factors, versatile interaction control and the development of a user-friendly interface, require further exploration before the practical application of HSI. This paper presents a unified HSI framework, UniHSI, which supports unified control of diverse interactions through language commands. This framework is built upon the definition of interaction as Chain of Contacts (CoC): steps of human joint-object part pairs, which is inspired by the strong correlation between interaction types and human-object contact regions. Based on the definition, UniHSI constitutes a Large Language Model (LLM) Planner to translate language prompts into task plans in the form of CoC, and a Unified Controller that turns CoC into uniform task execution. To facilitate training and evaluation, we collect a new dataset named ScenePlan that encompasses thousands of task plans generated by LLMs based on diverse scenarios. Comprehensive experiments demonstrate the effectiveness of our framework in versatile task execution and generalizability to real scanned scenes. The project page is at https://github.com/OpenRobotLab/UniHSI .