We propose Latent-Shift -- an efficient text-to-video generation method based on a pretrained text-to-image generation model that consists of an autoencoder and a U-Net diffusion model. Learning a video diffusion model in the latent space is much more efficient than in the pixel space. The latter is often limited to first generating a low-resolution video followed by a sequence of frame interpolation and super-resolution models, which makes the entire pipeline very complex and computationally expensive. To extend a U-Net from image generation to video generation, prior work proposes to add additional modules like 1D temporal convolution and/or temporal attention layers. In contrast, we propose a parameter-free temporal shift module that can leverage the spatial U-Net as is for video generation. We achieve this by shifting two portions of the feature map channels forward and backward along the temporal dimension. The shifted features of the current frame thus receive the features from the previous and the subsequent frames, enabling motion learning without additional parameters. We show that Latent-Shift achieves comparable or better results while being significantly more efficient. Moreover, Latent-Shift can generate images despite being finetuned for T2V generation.
Plain text has become a prevalent interface for text-to-image synthesis. However, its limited customization options hinder users from accurately describing desired outputs. For example, plain text makes it hard to specify continuous quantities, such as the precise RGB color value or importance of each word. Furthermore, creating detailed text prompts for complex scenes is tedious for humans to write and challenging for text encoders to interpret. To address these challenges, we propose using a rich-text editor supporting formats such as font style, size, color, and footnote. We extract each word's attributes from rich text to enable local style control, explicit token reweighting, precise color rendering, and detailed region synthesis. We achieve these capabilities through a region-based diffusion process. We first obtain each word's region based on cross-attention maps of a vanilla diffusion process using plain text. For each region, we enforce its text attributes by creating region-specific detailed prompts and applying region-specific guidance. We present various examples of image generation from rich text and demonstrate that our method outperforms strong baselines with quantitative evaluations.
Smartphone cameras today are increasingly approaching the versatility and quality of professional cameras through a combination of hardware and software advancements. However, fixed aperture remains a key limitation, preventing users from controlling the depth of field (DoF) of captured images. At the same time, many smartphones now have multiple cameras with different fixed apertures -- specifically, an ultra-wide camera with wider field of view and deeper DoF and a higher resolution primary camera with shallower DoF. In this work, we propose $\text{DC}^2$, a system for defocus control for synthetically varying camera aperture, focus distance and arbitrary defocus effects by fusing information from such a dual-camera system. Our key insight is to leverage real-world smartphone camera dataset by using image refocus as a proxy task for learning to control defocus. Quantitative and qualitative evaluations on real-world data demonstrate our system's efficacy where we outperform state-of-the-art on defocus deblurring, bokeh rendering, and image refocus. Finally, we demonstrate creative post-capture defocus control enabled by our method, including tilt-shift and content-based defocus effects.
Novel view synthesis from a single image has been a cornerstone problem for many Virtual Reality applications that provide immersive experiences. However, most existing techniques can only synthesize novel views within a limited range of camera motion or fail to generate consistent and high-quality novel views under significant camera movement. In this work, we propose a pose-guided diffusion model to generate a consistent long-term video of novel views from a single image. We design an attention layer that uses epipolar lines as constraints to facilitate the association between different viewpoints. Experimental results on synthetic and real-world datasets demonstrate the effectiveness of the proposed diffusion model against state-of-the-art transformer-based and GAN-based approaches.
We present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.
Close-up facial images captured at close distances often suffer from perspective distortion, resulting in exaggerated facial features and unnatural/unattractive appearances. We propose a simple yet effective method for correcting perspective distortions in a single close-up face. We first perform GAN inversion using a perspective-distorted input facial image by jointly optimizing the camera intrinsic/extrinsic parameters and face latent code. To address the ambiguity of joint optimization, we develop focal length reparametrization, optimization scheduling, and geometric regularization. Re-rendering the portrait at a proper focal length and camera distance effectively corrects these distortions and produces more natural-looking results. Our experiments show that our method compares favorably against previous approaches regarding visual quality. We showcase numerous examples validating the applicability of our method on portrait photos in the wild.
There has been tremendous progress in large-scale text-to-image synthesis driven by diffusion models enabling versatile downstream applications such as 3D object synthesis from texts, image editing, and customized generation. We present a generic approach using latent diffusion models as powerful image priors for various visual synthesis tasks. Existing methods that utilize such priors fail to use these models' full capabilities. To improve this, our core ideas are 1) a feature matching loss between features from different layers of the decoder to provide detailed guidance and 2) a KL divergence loss to regularize the predicted latent features and stabilize the training. We demonstrate the efficacy of our approach on three different applications, text-to-3D, StyleGAN adaptation, and layered image editing. Extensive results show our method compares favorably against baselines.
3D-aware GANs offer new capabilities for creative content editing, such as view synthesis, while preserving the editing capability of their 2D counterparts. Using GAN inversion, these methods can reconstruct an image or a video by optimizing/predicting a latent code and achieve semantic editing by manipulating the latent code. However, a model pre-trained on a face dataset (e.g., FFHQ) often has difficulty handling faces with out-of-distribution (OOD) objects, (e.g., heavy make-up or occlusions). We address this issue by explicitly modeling OOD objects in face videos. Our core idea is to represent the face in a video using two neural radiance fields, one for in-distribution and the other for out-of-distribution data, and compose them together for reconstruction. Such explicit decomposition alleviates the inherent trade-off between reconstruction fidelity and editability. We evaluate our method's reconstruction accuracy and editability on challenging real videos and showcase favorable results against other baselines.
Temporal consistency is essential for video editing applications. Existing work on layered representation of videos allows propagating edits consistently to each frame. These methods, however, can only edit object appearance rather than object shape changes due to the limitation of using a fixed UV mapping field for texture atlas. We present a shape-aware, text-driven video editing method to tackle this challenge. To handle shape changes in video editing, we first propagate the deformation field between the input and edited keyframe to all frames. We then leverage a pre-trained text-conditioned diffusion model as guidance for refining shape distortion and completing unseen regions. The experimental results demonstrate that our method can achieve shape-aware consistent video editing and compare favorably with the state-of-the-art.
Dynamic radiance field reconstruction methods aim to model the time-varying structure and appearance of a dynamic scene. Existing methods, however, assume that accurate camera poses can be reliably estimated by Structure from Motion (SfM) algorithms. These methods, thus, are unreliable as SfM algorithms often fail or produce erroneous poses on challenging videos with highly dynamic objects, poorly textured surfaces, and rotating camera motion. We address this robustness issue by jointly estimating the static and dynamic radiance fields along with the camera parameters (poses and focal length). We demonstrate the robustness of our approach via extensive quantitative and qualitative experiments. Our results show favorable performance over the state-of-the-art dynamic view synthesis methods.