Abstract:Due to the fascinating generative performance of text-to-image diffusion models, growing text-to-3D generation works explore distilling the 2D generative priors into 3D, using the score distillation sampling (SDS) loss, to bypass the data scarcity problem. The existing text-to-3D methods have achieved promising results in realism and 3D consistency, but text-to-4D generation still faces challenges, including lack of realism and insufficient dynamic motions. In this paper, we propose a novel method for text-to-4D generation, which ensures the dynamic amplitude and authenticity through direct supervision provided by a video prior. Specifically, we adopt a text-to-video diffusion model to generate a reference video and divide 4D generation into two stages: static generation and dynamic generation. The static 3D generation is achieved under the guidance of the input text and the first frame of the reference video, while in the dynamic generation stage, we introduce a customized SDS loss to ensure multi-view consistency, a video-based SDS loss to improve temporal consistency, and most importantly, direct priors from the reference video to ensure the quality of geometry and texture. Moreover, we design a prior-switching training strategy to avoid conflicts between different priors and fully leverage the benefits of each prior. In addition, to enrich the generated motion, we further introduce a dynamic modeling representation composed of a deformation network and a topology network, which ensures dynamic continuity while modeling topological changes. Our method not only supports text-to-4D generation but also enables 4D generation from monocular videos. The comparison experiments demonstrate the superiority of our method compared to existing methods.
Abstract:SVG (Scalable Vector Graphics) is a widely used graphics format that possesses excellent scalability and editability. Image vectorization, which aims to convert raster images to SVGs, is an important yet challenging problem in computer vision and graphics. Existing image vectorization methods either suffer from low reconstruction accuracy for complex images or require long computation time. To address this issue, we propose SuperSVG, a superpixel-based vectorization model that achieves fast and high-precision image vectorization. Specifically, we decompose the input image into superpixels to help the model focus on areas with similar colors and textures. Then, we propose a two-stage self-training framework, where a coarse-stage model is employed to reconstruct the main structure and a refinement-stage model is used for enriching the details. Moreover, we propose a novel dynamic path warping loss to help the refinement-stage model to inherit knowledge from the coarse-stage model. Extensive qualitative and quantitative experiments demonstrate the superior performance of our method in terms of reconstruction accuracy and inference time compared to state-of-the-art approaches. The code is available in \url{https://github.com/sjtuplayer/SuperSVG}.
Abstract:Due to the complex physical properties of granular materials, research on robot learning for manipulating such materials predominantly either disregards the consideration of their physical characteristics or uses surrogate models to approximate their physical properties. Learning to manipulate granular materials based on physical information obtained through precise modelling remains an unsolved problem. In this paper, we propose to address this challenge by constructing a differentiable physics simulator for granular materials based on the Taichi programming language and developing a learning framework accelerated by imperfect demonstrations that are generated via gradient-based optimisation on non-granular materials through our simulator. Experimental results show that our method trains three policies that, when chained, are capable of executing the task of transporting granular materials in both simulated and real-world scenarios, which existing popular deep reinforcement learning models fail to accomplish.
Abstract:The burgeoning field of text-based video generation (T2V) has reignited significant interest in the research of controllable video editing. Although pre-trained T2V-based editing models have achieved efficient editing capabilities, current works are still plagued by two major challenges. Firstly, the inherent limitations of T2V models lead to content inconsistencies and motion discontinuities between frames. Secondly, the notorious issue of over-editing significantly disrupts areas that are intended to remain unaltered. To address these challenges, our work aims to explore a robust video-based editing paradigm based on score distillation. Specifically, we propose an Adaptive Sliding Score Distillation strategy, which not only enhances the stability of T2V supervision but also incorporates both global and local video guidance to mitigate the impact of generation errors. Additionally, we modify the self-attention layers during the editing process to further preserve the key features of the original video. Extensive experiments demonstrate that these strategies enable us to effectively address the aforementioned challenges, achieving superior editing performance compared to existing state-of-the-art methods.
Abstract:Inspired by the software industry's practice of offering different editions or versions of a product tailored to specific user groups or use cases, we propose a novel task, namely, training-free editioning, for text-to-image models. Specifically, we aim to create variations of a base text-to-image model without retraining, enabling the model to cater to the diverse needs of different user groups or to offer distinct features and functionalities. To achieve this, we propose that different editions of a given text-to-image model can be formulated as concept subspaces in the latent space of its text encoder (e.g., CLIP). In such a concept subspace, all points satisfy a specific user need (e.g., generating images of a cat lying on the grass/ground/falling leaves). Technically, we apply Principal Component Analysis (PCA) to obtain the desired concept subspaces from representative text embedding that correspond to a specific user need or requirement. Projecting the text embedding of a given prompt into these low-dimensional subspaces enables efficient model editioning without retraining. Intuitively, our proposed editioning paradigm enables a service provider to customize the base model into its "cat edition" (or other editions) that restricts image generation to cats, regardless of the user's prompt (e.g., dogs, people, etc.). This introduces a new dimension for product differentiation, targeted functionality, and pricing strategies, unlocking novel business models for text-to-image generators. Extensive experimental results demonstrate the validity of our approach and its potential to enable a wide range of customized text-to-image model editions across various domains and applications.
Abstract:Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstruction and editing results but suffer from inefficiency in rendering. Gaussian splatting significantly accelerates rendering by rasterizing Gaussian ellipsoids. However, Gaussian splatting utilizes a single Spherical Harmonic (SH) function to model both texture and lighting, limiting independent editing capabilities of these components. Recently, attempts have been made to decouple texture and lighting with the Gaussian splatting representation but may fail to produce plausible geometry and decomposition results on reflective scenes. Additionally, the forward shading technique they employ introduces noticeable blending artifacts during relighting, as the geometry attributes of Gaussians are optimized under the original illumination and may not be suitable for novel lighting conditions. To address these issues, we introduce DeferredGS, a method for decoupling and editing the Gaussian splatting representation using deferred shading. To achieve successful decoupling, we model the illumination with a learnable environment map and define additional attributes such as texture parameters and normal direction on Gaussians, where the normal is distilled from a jointly trained signed distance function. More importantly, we apply deferred shading, resulting in more realistic relighting effects compared to previous methods. Both qualitative and quantitative experiments demonstrate the superior performance of DeferredGS in novel view synthesis and editing tasks.
Abstract:3D Gaussian splatting, emerging as a groundbreaking approach, has drawn increasing attention for its capabilities of high-fidelity reconstruction and real-time rendering. However, it couples the appearance and geometry of the scene within the Gaussian attributes, which hinders the flexibility of editing operations, such as texture swapping. To address this issue, we propose a novel approach, namely Texture-GS, to disentangle the appearance from the geometry by representing it as a 2D texture mapped onto the 3D surface, thereby facilitating appearance editing. Technically, the disentanglement is achieved by our proposed texture mapping module, which consists of a UV mapping MLP to learn the UV coordinates for the 3D Gaussian centers, a local Taylor expansion of the MLP to efficiently approximate the UV coordinates for the ray-Gaussian intersections, and a learnable texture to capture the fine-grained appearance. Extensive experiments on the DTU dataset demonstrate that our method not only facilitates high-fidelity appearance editing but also achieves real-time rendering on consumer-level devices, e.g. a single RTX 2080 Ti GPU.
Abstract:Neural implicit representations, including Neural Distance Fields and Neural Radiance Fields, have demonstrated significant capabilities for reconstructing surfaces with complicated geometry and topology, and generating novel views of a scene. Nevertheless, it is challenging for users to directly deform or manipulate these implicit representations with large deformations in the real-time fashion. Gaussian Splatting(GS) has recently become a promising method with explicit geometry for representing static scenes and facilitating high-quality and real-time synthesis of novel views. However,it cannot be easily deformed due to the use of discrete Gaussians and lack of explicit topology. To address this, we develop a novel GS-based method that enables interactive deformation. Our key idea is to design an innovative mesh-based GS representation, which is integrated into Gaussian learning and manipulation. 3D Gaussians are defined over an explicit mesh, and they are bound with each other: the rendering of 3D Gaussians guides the mesh face split for adaptive refinement, and the mesh face split directs the splitting of 3D Gaussians. Moreover, the explicit mesh constraints help regularize the Gaussian distribution, suppressing poor-quality Gaussians(e.g. misaligned Gaussians,long-narrow shaped Gaussians), thus enhancing visual quality and avoiding artifacts during deformation. Based on this representation, we further introduce a large-scale Gaussian deformation technique to enable deformable GS, which alters the parameters of 3D Gaussians according to the manipulation of the associated mesh. Our method benefits from existing mesh deformation datasets for more realistic data-driven Gaussian deformation. Extensive experiments show that our approach achieves high-quality reconstruction and effective deformation, while maintaining the promising rendering results at a high frame rate(65 FPS on average).
Abstract:In this paper, we introduce the Volumetric Relightable Morphable Model (VRMM), a novel volumetric and parametric facial prior for 3D face modeling. While recent volumetric prior models offer improvements over traditional methods like 3D Morphable Models (3DMMs), they face challenges in model learning and personalized reconstructions. Our VRMM overcomes these by employing a novel training framework that efficiently disentangles and encodes latent spaces of identity, expression, and lighting into low-dimensional representations. This framework, designed with self-supervised learning, significantly reduces the constraints for training data, making it more feasible in practice. The learned VRMM offers relighting capabilities and encompasses a comprehensive range of expressions. We demonstrate the versatility and effectiveness of VRMM through various applications like avatar generation, facial reconstruction, and animation. Additionally, we address the common issue of overfitting in generative volumetric models with a novel prior-preserving personalization framework based on VRMM. Such an approach enables accurate 3D face reconstruction from even a single portrait input. Our experiments showcase the potential of VRMM to significantly enhance the field of 3D face modeling.
Abstract:The generation of 3D clothed humans has attracted increasing attention in recent years. However, existing work cannot generate layered high-quality 3D humans with consistent body structures. As a result, these methods are unable to arbitrarily and separately change and edit the body and clothing of the human. In this paper, we propose a text-driven layered 3D human generation framework based on a novel physically-decoupled semantic-aware diffusion model. To keep the generated clothing consistent with the target text, we propose a semantic-confidence strategy for clothing that can eliminate the non-clothing content generated by the model. To match the clothing with different body shapes, we propose a SMPL-driven implicit field deformation network that enables the free transfer and reuse of clothing. Besides, we introduce uniform shape priors based on the SMPL model for body and clothing, respectively, which generates more diverse 3D content without being constrained by specific templates. The experimental results demonstrate that the proposed method not only generates 3D humans with consistent body structures but also allows free editing in a layered manner. The source code will be made public.