Recent CLIP-guided 3D optimization methods, e.g., DreamFields and PureCLIPNeRF achieve great success in zero-shot text-guided 3D synthesis. However, due to the scratch training and random initialization without any prior knowledge, these methods usually fail to generate accurate and faithful 3D structures that conform to the corresponding text. In this paper, we make the first attempt to introduce the explicit 3D shape prior to CLIP-guided 3D optimization methods. Specifically, we first generate a high-quality 3D shape from input texts in the text-to-shape stage as the 3D shape prior. We then utilize it as the initialization of a neural radiance field and then optimize it with the full prompt. For the text-to-shape generation, we present a simple yet effective approach that directly bridges the text and image modalities with a powerful text-to-image diffusion model. To narrow the style domain gap between images synthesized by the text-to-image model and shape renderings used to train the image-to-shape generator, we further propose to jointly optimize a learnable text prompt and fine-tune the text-to-image diffusion model for rendering-style image generation. Our method, namely, Dream3D, is capable of generating imaginative 3D content with better visual quality and shape accuracy than state-of-the-art methods.

To reproduce the success of text-to-image (T2I) generation, recent works in text-to-video (T2V) generation employ large-scale text-video dataset for fine-tuning. However, such paradigm is computationally expensive. Humans have the amazing ability to learn new visual concepts from just one single exemplar. We hereby study a new T2V generation problem$\unicode{x2014}$One-Shot Video Generation, where only a single text-video pair is presented for training an open-domain T2V generator. Intuitively, we propose to adapt the T2I diffusion model pretrained on massive image data for T2V generation. We make two key observations: 1) T2I models are able to generate images that align well with the verb terms; 2) extending T2I models to generate multiple images concurrently exhibits surprisingly good content consistency. To further learn continuous motion, we propose Tune-A-Video with a tailored Sparse-Causal Attention, which generates videos from text prompts via an efficient one-shot tuning of pretrained T2I diffusion models. Tune-A-Video is capable of producing temporally-coherent videos over various applications such as change of subject or background, attribute editing, style transfer, demonstrating the versatility and effectiveness of our method.

The recurrent structure is a prevalent framework for the task of video super-resolution, which models the temporal dependency between frames via hidden states. When applied to real-world scenarios with unknown and complex degradations, hidden states tend to contain unpleasant artifacts and propagate them to restored frames. In this circumstance, our analyses show that such artifacts can be largely alleviated when the hidden state is replaced with a cleaner counterpart. Based on the observations, we propose a Hidden State Attention (HSA) module to mitigate artifacts in real-world video super-resolution. Specifically, we first adopt various cheap filters to produce a hidden state pool. For example, Gaussian blur filters are for smoothing artifacts while sharpening filters are for enhancing details. To aggregate a new hidden state that contains fewer artifacts from the hidden state pool, we devise a Selective Cross Attention (SCA) module, in which the attention between input features and each hidden state is calculated. Equipped with HSA, our proposed method, namely FastRealVSR, is able to achieve 2x speedup while obtaining better performance than Real-BasicVSR. Codes will be available at https://github.com/TencentARC/FastRealVSR

Vector-Quantized (VQ-based) generative models usually consist of two basic components, i.e., VQ tokenizers and generative transformers. Prior research focuses on improving the reconstruction fidelity of VQ tokenizers but rarely examines how the improvement in reconstruction affects the generation ability of generative transformers. In this paper, we surprisingly find that improving the reconstruction fidelity of VQ tokenizers does not necessarily improve the generation. Instead, learning to compress semantic features within VQ tokenizers significantly improves generative transformers' ability to capture textures and structures. We thus highlight two competing objectives of VQ tokenizers for image synthesis: semantic compression and details preservation. Different from previous work that only pursues better details preservation, we propose Semantic-Quantized GAN (SeQ-GAN) with two learning phases to balance the two objectives. In the first phase, we propose a semantic-enhanced perceptual loss for better semantic compression. In the second phase, we fix the encoder and codebook, but enhance and finetune the decoder to achieve better details preservation. The proposed SeQ-GAN greatly improves VQ-based generative models and surpasses the GAN and Diffusion Models on both unconditional and conditional image generation. Our SeQ-GAN (364M) achieves Frechet Inception Distance (FID) of 6.25 and Inception Score (IS) of 140.9 on 256x256 ImageNet generation, a remarkable improvement over VIT-VQGAN (714M), which obtains 11.2 FID and 97.2 IS.

Recently, a surge of high-quality 3D-aware GANs have been proposed, which leverage the generative power of neural rendering. It is natural to associate 3D GANs with GAN inversion methods to project a real image into the generator's latent space, allowing free-view consistent synthesis and editing, referred as 3D GAN inversion. Although with the facial prior preserved in pre-trained 3D GANs, reconstructing a 3D portrait with only one monocular image is still an ill-pose problem. The straightforward application of 2D GAN inversion methods focuses on texture similarity only while ignoring the correctness of 3D geometry shapes. It may raise geometry collapse effects, especially when reconstructing a side face under an extreme pose. Besides, the synthetic results in novel views are prone to be blurry. In this work, we propose a novel method to promote 3D GAN inversion by introducing facial symmetry prior. We design a pipeline and constraints to make full use of the pseudo auxiliary view obtained via image flipping, which helps obtain a robust and reasonable geometry shape during the inversion process. To enhance texture fidelity in unobserved viewpoints, pseudo labels from depth-guided 3D warping can provide extra supervision. We design constraints aimed at filtering out conflict areas for optimization in asymmetric situations. Comprehensive quantitative and qualitative evaluations on image reconstruction and editing demonstrate the superiority of our method.

High-fidelity facial avatar reconstruction from a monocular video is a significant research problem in computer graphics and computer vision. Recently, Neural Radiance Field (NeRF) has shown impressive novel view rendering results and has been considered for facial avatar reconstruction. However, the complex facial dynamics and missing 3D information in monocular videos raise significant challenges for faithful facial reconstruction. In this work, we propose a new method for NeRF-based facial avatar reconstruction that utilizes 3D-aware generative prior. Different from existing works that depend on a conditional deformation field for dynamic modeling, we propose to learn a personalized generative prior, which is formulated as a local and low dimensional subspace in the latent space of 3D-GAN. We propose an efficient method to construct the personalized generative prior based on a small set of facial images of a given individual. After learning, it allows for photo-realistic rendering with novel views and the face reenactment can be realized by performing navigation in the latent space. Our proposed method is applicable for different driven signals, including RGB images, 3DMM coefficients, and audios. Compared with existing works, we obtain superior novel view synthesis results and faithfully face reenactment performance.

In this study, we explore the representation mapping from the domain of visual arts to the domain of music, with which we can use visual arts as an effective handle to control music generation. Unlike most studies in multimodal representation learning that are purely data-driven, we adopt an analysis-by-synthesis approach that combines deep music representation learning with user studies. Such an approach enables us to discover \textit{interpretable} representation mapping without a huge amount of paired data. In particular, we discover that visual-to-music mapping has a nice property similar to equivariant. In other words, we can use various image transformations, say, changing brightness, changing contrast, style transfer, to control the corresponding transformations in the music domain. In addition, we released the Vis2Mus system as a controllable interface for symbolic music generation.

在本文中，我们为音乐驱动的舞蹈运动综合构成了一个新颖的框架，并具有可控的关键姿势约束。与仅基于音乐生成舞蹈运动序列的方法相反，该工作的目标是综合由音乐驱动的高质量舞蹈运动以及用户执行的定制姿势。我们的模型涉及两个用于音乐和运动表示形式的单模式变压器编码器，以及用于舞蹈动作生成的跨模式变压器解码器。跨模式变压器解码器可以通过引入局部邻居位置嵌入来使其合成平滑舞蹈运动序列合成平滑舞蹈运动序列的能力。这种机制使解码器对关键姿势和相应位置更加敏感。我们的舞蹈合成模型通过广泛的实验在定量和定性评估上取得了令人满意的表现，这证明了我们提出的方法的有效性。

尽管事实证明，视听表征适用于许多下游任务，但舞蹈视频的表示，这是更具体的，并且总是伴随着具有复杂听觉内容的音乐，但仍然具有挑战性且没有评估。考虑到舞者和音乐节奏的节奏运动之间的内在结合，我们介绍了Mudar，这是一个新颖的音乐舞蹈表示学习框架，以明确和隐性的方式执行音乐和舞蹈节奏的同步。具体而言，我们根据音乐节奏分析启发的视觉外观和运动提示得出舞蹈节奏。然后，视觉节奏在时间上与音乐对应物对齐，这些音乐由声音强度的幅度提取。同时，我们利用对比度学习在音频和视觉流中隐含的节奏的隐式连贯性。该模型通过预测视听对之间的时间一致性来学习关节嵌入。音乐舞蹈表示以及检测音频和视觉节奏的能力，可以进一步应用于三个下游任务：（a）舞蹈分类，（b）音乐舞蹈检索，以及（c）音乐舞蹈重新定位。广泛的实验表明，我们提出的框架以大幅度优于其他自我监督方法。

本文解决了对预先训练的深神经网络进行排名并筛选最下游任务的重要问题。这是具有挑战性的，因为每个任务的基本模型排名只能通过微调目标数据集中的预训练模型来生成，该模型是蛮力且计算昂贵的。最近的高级方法提出了几个轻巧的可转移性指标来预测微调结果。但是，这些方法仅捕获静态表示，但忽略了微调动态。为此，本文提出了一个新的可传递性度量，称为\ textbf {s} elf-challenging \ textbf {f} isher \ textbf {d} is Criminant \ textbf {a} nalisy（\ textbf {\ textbf {sfda}）现有作品没有的有吸引力的好处。首先，SFDA可以将静态特征嵌入渔民空间中，并完善它们，以在类之间更好地分离性。其次，SFDA使用一种自我挑战的机制来鼓励不同的预训练模型来区分硬性示例。第三，SFDA可以轻松地为模型集合选择多个预训练的模型。 $ 33 $预培训的$ 11 $下游任务的$ 33 $预培训模型的广泛实验表明，在测量预训练模型的可传递性时，SFDA具有高效，有效和健壮。例如，与最先进的方法NLEEP相比，SFDA平均显示了59.1美元的增益，同时带来了$ 22.5 $ x的墙壁速度速度。该代码将在\ url {https://github.com/tencentarc/sfda}上提供。