3D Gaussian Splatting (3DGS) has emerged as the state-of-the-art 3D reconstruction technique, offering high-quality results with fast training and rendering. However, its expressivity is limited as pixels covered by the same Gaussian share identical colors aside from a Gaussian falloff scaling factor, and individual Gaussians can only represent simple ellipsoids geometrically. To overcome these limitations, we integrate texture and alpha mapping from traditional graphics with 3DGS. Our approach augments each Gaussian with alpha, RGB, or RGBA texture maps to model spatially varying color and opacity across each Gaussian’s extent. This allows Gaussians to represent richer texture patterns and geometric structures beyond single-color ellipsoids. Notably, alpha-only texture maps significantly improve Gaussian expressivity, while further augmenting with RGB texture maps achieve maximum expressivity. We validate our method on a wide variety of standard benchmark datasets and our own custom captures at both the object and scene levels, and demonstrate image quality improvements over existing methods while using a similar or lower number of Gaussians.

We introduce the Deformable Gaussian Splats Large Reconstruction Model (DGS-LRM), the first feed-forward method predicting deformable 3D Gaussian splats from a monocular posed video of any dynamic scene. Feed-forward scene reconstruction has gained significant attention for its ability to rapidly create digital replicas of real-world environments. However, most existing models are limited to static scenes and fail to reconstruct the motion of moving objects. Developing a feed-forward model for dynamic scene reconstruction poses significant challenges, including the scarcity of training data and the need for appropriate 3D representations and training paradigms. To address these challenges, we introduce several key technical contributions: an enhanced large-scale synthetic dataset with ground-truth multi-view videos and dense 3D scene flow supervision; a per-pixel deformable 3D Gaussian representation that is easy to learn, supports high-quality dynamic view synthesis, and enables long-range 3D tracking; and a large transformer network that achieves real-time, generalizable dynamic scene reconstruction. Extensive qualitative and quantitative experiments demonstrate that DGS-LRM achieves dynamic scene reconstruction quality comparable to optimization-based methods, while significantly outperforming the state-of-the-art predictive dynamic reconstruction method on real-world examples. Its predicted physically grounded 3D deformation is accurate and can be readily adapted for long-range 3D tracking tasks, achieving performance on par with state-of-the-art monocular video 3D tracking methods.

Contents generated by recent advanced Text-to-Image (T2I) diffusion models are sometimes too imaginative for existing off-the-shelf dense predictors to estimate due to the immitigable domain gap. We introduce DMP, a pipeline utilizing pre-trained T2I models as a prior for dense prediction tasks. To address the misalignment between deterministic prediction tasks and stochastic T2I models, we reformulate the diffusion process through a sequence of interpo-lations, establishing a deterministic mapping between input RGB images and output prediction distributions. To preserve generalizability, we use low-rank adaptation to fine-tune pre-trained models. Extensive experiments across five tasks, including 3D property estimation, semantic segmentation, and intrinsic image decomposition, showcase the efficacy of the proposed method. Despite limited-domain training data, the approach yields faithful estimations for arbitrary images, surpassing existing state-of-the-art algorithms. The code is available at https://github.com/shinying/dmp.

3D asset generation is getting massive amounts of attention, inspired by the recent success of text-guided 2D content creation. Existing text-to-3D methods use pretrained text-to-image diffusion models in an optimization problem or fine-tune them on synthetic data, which often results in non-photorealistic 3D objects without backgrounds. In this paper, we present a method that leverages pretrained text-to-image models as a prior, and learn to generate multi-view images in a single denoising process from real-world data. Concretely, we propose to integrate 3D volume-rendering and cross-frame-attention layers into each block of the existing U-Net network of the text-to-image model. Moreover, we design an autoregressive generation that renders more 3D-consistent images at any viewpoint. We train our model on real-world datasets of objects and showcase its capabilities to generate instances with a variety of high-quality shapes and textures in authentic surroundings. Compared to the existing methods, the results generated by our method are consistent, and have favorable visual quality (−30% FID, −37% KID).

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.

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. More qualitative results are available at https://poseguided-diffusion.github.io/.

Recent studies have shown that paddings in convolutional neural networks encode absolute position information which can negatively affect the model performance for certain tasks. However, existing metrics for quantifying the strength of positional information remain unreliable and frequently lead to erroneous results. To address this issue, we propose novel metrics for measuring and visualizing the encoded positional information. We formally define the encoded information as Position-information Pattern from Padding (PPP) and conduct a series of experiments to study its properties as well as its formation. The proposed metrics measure the presence of positional information more reliably than the existing metrics based on PosENet and tests in F-Conv. We also demonstrate that for any extant (and proposed) padding schemes, PPP is primarily a learning artifact and is less dependent on the characteristics of the underlying padding schemes.

We present an approach to generate a 360-degree view of a person with a consistent, high-resolution appearance from a single input image. NeRF and its variants typically require videos or images from different viewpoints. Most existing approaches taking monocular input either rely on ground-truth 3D scans for supervision or lack 3D consistency. While recent 3D generative models show promise of 3D consistent human digitization, these approaches do not generalize well to diverse clothing appearances, and the results lack photorealism. Unlike existing work, we utilize high-capacity 2D diffusion models pretrained for general image synthesis tasks as an appearance prior of clothed humans. To achieve better 3D consistency while retaining the input identity, we progressively synthesize multiple views of the human in the input image by inpainting missing regions with shape-guided diffusion conditioned on silhouette and surface normal. We then fuse these synthesized multi-view images via inverse rendering to obtain a fully textured high-resolution 3D mesh of the given person. Experiments show that our approach outperforms prior methods and achieves photorealistic 360-degree synthesis of a wide range of clothed humans with complex textures from a single image.

Generating images from hand-drawings is a crucial and fundamental task in content creation. The translation is difficult as there exist infinite possibilities and the different users usually expect different outcomes. Therefore, we propose a unified framework supporting a three-dimensional control over the image synthesis from sketches and strokes based on diffusion models. Users can not only decide the level of faithfulness to the input strokes and sketches, but also the degree of realism, as the user inputs are usually not consistent with the real images. Qualitative and quantitative experiments demonstrate that our framework achieves state-of-the-art performance while providing flexibility in generating customized images with control over shape, color, and realism. Moreover, our method unleashes applications such as editing on real images, generation with partial sketches and strokes, and multi-domain multi-modal synthesis.

In this work, we aim to address the 3D scene stylization problem - generating stylized images of the scene at arbitrary novel view angles. A straightforward solution is to combine existing novel view synthesis and image/video style transfer approaches, which often leads to blurry results or inconsistent appearance. Inspired by the high-quality results of the neural radiance fields (NeRF) method, we propose a joint framework to directly render novel views with the desired style. Our framework consists of two components: an implicit representation of the 3D scene with the neural radiance fields model, and a hypernetwork to transfer the style information into the scene representation. To alleviate the training difficulties and memory burden, we propose a two-stage training procedure and a patch sub-sampling approach to optimize the style and content losses with the neural radiance fields model. After optimization, our model is able to render consistent novel views at arbitrary view angles with arbitrary style. Both quantitative evaluation and human subject study have demonstrated that the proposed method generates faithful stylization results with consistent appearance across different views.

Recent years have witnessed the rapid progress of generative adversarial networks (GANs). However, the success of the GAN models hinges on a large amount of training data. This work proposes a regularization approach for training robust GAN models on limited data. We theoretically show a connection between the regularized loss and an f-divergence called LeCam-divergence, which we find is more robust under limited training data. Extensive experiments on several benchmark datasets demonstrate that the proposed regularization scheme 1) improves the generalization performance and stabilizes the learning dynamics of GAN models under limited training data, and 2) complements the recent data augmentation methods. These properties facilitate training GAN models to achieve state-of-theart performance when only limited training data of the ImageNet benchmark is available. The source code is available at https://github.com/google/lecam-gan.

We tackle a 3D scene stylization problem — generating stylized images of a scene from arbitrary novel views given a set of images of the same scene and a reference image of the desired style as inputs. Direct solution of combining novel view synthesis and stylization approaches lead to results that are blurry or not consistent across different views. We propose a point cloud-based method for consistent 3D scene stylization. First, we construct the point cloud by back-projecting the image features to the 3D space. Second, we develop point cloud aggregation modules to gather the style information of the 3D scene, and then modulate the features in the point cloud with a linear transformation matrix. Finally, we project the transformed features to 2D space to obtain the novel views. Experimental results on two diverse datasets of real-world scenes validate that our method generates consistent stylized novel view synthesis results against other alternative approaches.

n recent years, text-guided image manipulation has gained increasing attention in the multimedia and computer vision community. The input to conditional image generation has evolved from image-only to multimodality. In this paper, we study a setting that allows users to edit an image with multiple objects using complex text instructions to add, remove, or change the objects. The inputs of the task are multimodal including (1) a reference image and (2) an instruction in natural language that describes desired modifications to the image. We propose a GAN-based method to tackle this problem. The key idea is to treat text as neural operators to locally modify the image feature. We show that the proposed model performs favorably against recent strong baselines on three public datasets. Specifically, it generates images of greater fidelity and semantic relevance, and when used as a image query, leads to better retrieval performance.

The audio-visual video parsing task aims to temporally parse a video into audio or visual event categories. However, it is labor intensive to temporally annotate audio and visual events and thus hampers the learning of a parsing model. To this end, we propose to explore additional cross-video and cross-modality supervisory signals to facilitate weakly-supervised audio-visual video parsing. The proposed method exploits both the common and diverse event semantics across videos to identify audio or visual events. In addition, our method explores event co-occurrence across audio, visual, and audio-visual streams. We leverage the explored cross-modality co-occurrence to localize segments of target events while excluding irrelevant ones. The discovered supervisory signals across different videos and modalities can greatly facilitate the training with only video-level annotations. Quantitative and qualitative results demonstrate that the proposed method performs favorably against existing methods on weakly-supervised audio-visual video parsing.

Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different distribution. Domain adaptation provides a solution by adapting existing labels to the target testing data. However, a large gap between domains could make adaptation a challenging task, which leads to unstable training processes and sub-optimal results. In this paper, we propose to bridge the domain gap with an intermediate domain and progressively solve easier adaptation subtasks. This intermediate domain is constructed by translating the source images to mimic the ones in the target domain. To tackle the domain-shift problem, we adopt adversarial learning to align distributions at the feature level. In addition, a weighted task loss is applied to deal with unbalanced image quality in the intermediate domain. Experimental results show that our method performs favorably against the state-of-the-art method in terms of the performance on the target domain.

Most conditional generation tasks expect diverse outputs given a single conditional context. However, conditional generative adversarial networks (cGANs) often focus on the prior conditional information and ignore the input noise vectors, which contribute to the output variations. Recent attempts to resolve the mode collapse issue for cGANs are usually task-specific and computationally expensive. In this work, we propose a simple yet effective regularization term to address the mode collapse issue for cGANs. The proposed method explicitly maximizes the ratio of the distance between generated images with respect to the corresponding latent codes, thus encouraging the generators to explore more minor modes during training. This mode seeking regularization term is readily applicable to various conditional generation tasks without imposing training overhead or modifying the original network structures. We validate the proposed algorithm on three conditional image synthesis tasks including categorical generation, image-to-image translation, and text-to-image synthesis with different baseline models. Both qualitative and quantitative results demonstrate the effectiveness of the proposed regularization method for improving diversity without loss of quality.

Spatial audio is an essential medium to audiences for 3D visual and auditory experience. However, the recording devices and techniques are expensive or inaccessible to the general public. In this work, we propose a self-supervised audio spatialization network that can generate spatial audio given the corresponding video and monaural audio. To enhance spatialization performance, we use an auxiliary classifier to classify ground-truth videos and those with audio where the left and right channels are swapped. We collect a large-scale video dataset with spatial audio to validate the proposed method. Experimental results demonstrate the effectiveness of the proposed model on the audio spatialization task.

Real-time recovering an accurate 6 DoF pose of a known planar target is essential for augmented reality and robotics applications. Despite several pose estimation tracking systems have been proposed over recent years, there is still the need for a more efficient and more accurate solution for general planar objects. In this work, we develop an innovative GPU implementation of a real-time pose estimation and tracking system. It consists of a pose estimation unit and a pose tracker unit. While the former computes an initial pose of a target using direct method, the latter realizes accurate pose tracking with a hierarchical search scheme. Experiments on both synthetic and real datasets demonstrate that the proposed algorithm performs favorably with various planar targets. By implementing our method on an embedded GPU, the system achieves to work at 11 FPS and is suitable for real-time applications.

Estimating 3D pose of a known object from a given 2D image is an important problem with numerous studies for robotics and augmented reality applications. While the state-of-the-art Perspective-n-Point algorithms perform well in pose estimation, the success hinges on whether feature points can be extracted and matched correctly on targets with rich texture. In this work, we propose a robust direct method for 3D pose estimation with high accuracy that performs well on both textured and textureless planar targets. First, the pose of a planar target with respect to a calibrated camera is approximately estimated by posing it as a template matching problem. Next, the object pose is further refined and disambiguated with a gradient descent search scheme. Extensive experiments on both synthetic and real datasets demonstrate the proposed direct pose estimation algorithm performs favorably against state-of-the-art feature-based approaches in terms of robustness and accuracy under several varying conditions.

This work presents LEaD, a helmet-based visual guidance system utilizing light movement in scooter drivers' peripheral vision for turn-by-turn navigation. A linear light strip mounted on a helmet navigates for scooter drivers using simple 1D light movement, which can be easily acquired and identified by peripheral vision with the on-going foveal vision task. User studies suggest that this novel system can effectively direct scooter drivers without introducing visual distractions in route-guided experiences.

This work describes a novel building block system for tangible interaction design, GaussBricks, which enables real-time constructive tangible interactions on portable displays. Given its simplicity, the mechanical design of the magnetic building blocks facilitates the construction of configurable forms. The form constructed by the magnetic building blocks, which are connected by the magnetic joints, allows users to stably manipulate with various elastic force feedback mechanisms. With an analog Hall-sensor grid mounted to its back, a portable display determines the geometrical configuration and detects various user interactions in real time. This work also introduce several methods to enable shape changing, multi-touch input, and display capabilities in the construction. The proposed building block system enriches how individuals interact with the portable displays physically.