Access to high-quality and diverse 3D articulated digital human assets is crucial in various applications, ranging from virtual reality to social platforms. Generative approaches, such as 3D generative adversarial networks (GANs), are rapidly replacing laborious manual content creation tools. Existing 3D GAN frameworks typically rely on explicit representations that are fast to render but offer limited quality, or implicit representations, which offer high capacity but are slow to render, thereby limiting the 3D fidelity in GAN settings. In this work, we introduce layered surface volumes (LSVs) as a new 3D representation for articulatable humans. LSVs represent a human body using multiple textured mesh layers around a conventional mesh template. The explicit mesh layers can be interpreted as a discretized volume with finite thickness located around the template manifold, as such it has the capacity to capture off-template details like hair or accessories, while at the same time it can profit from mesh rasterization for fast rendering. LSVs can be articulated, and they exhibit exceptional efficiency in GAN settings. Trained on unstructured, single-view 2D image datasets, our LSV-GAN generates high-quality and viewconsistent 3D articulated digital humans without the need for view-inconsistent 2D upsampling networks. Project page can be found here.

Capturing images is a key part of automation for high-level tasks such as scene text recognition. Low-light conditions pose a challenge for high-level perception stacks, which are often optimized on well-lit, artifact-free images. Reconstruction methods for low-light images can produce well-lit counterparts, but typically at the cost of high-frequency details critical for downstream tasks. We propose Diffusion in the Dark (DiD), a diffusion model for low-light image reconstruction for text recognition. DiD provides qualitatively competitive reconstructions with that of state-of-the-art (SOTA), while preserving high-frequency details even in extremely noisy, dark conditions. We demonstrate that DiD, without any task-specific optimization, can outperform SOTA low-light methods in low-light text recognition on real images, bolstering the potential of diffusion models to solve ill-posed inverse problems. Our code and pretrained models can be found on https://ccnguyen.github.io/diffusion-in-the-dark/.

We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image. Our model samples from the distribution of possible renderings consistent with the input and, even in the presence of ambiguity, is capable of rendering diverse and plausible novel views. To achieve this, our method makes use of existing 2D diffusion backbones but, crucially, incorporates geometry priors in the form of a 3D feature volume. This latent feature field captures the distribution over possible scene representations and improves our method’s ability to generate view-consistent novel renderings. In addition to generating novel views, our method has the ability to autoregressively synthesize 3D-consistent sequences. We demonstrate state-of-the-art results on synthetic renderings and room-scale scenes; we also show compelling results for challenging, real-world objects.

Unsupervised learning of 3D-aware generative adversarial networks (GANs) using only collections of single-view 2D photographs has very recently made much progress. These 3D GANs, however, have not been demonstrated for human bodies and the generated radiance fields of existing frameworks are not directly editable, limiting their applicability in downstream tasks. We propose a solution to these challenges by developing a 3D GAN framework that learns to generate radiance fields of human bodies or faces in a canonical pose and warp them using an explicit deformation field into a desired body pose or facial expression. Using our framework, we demonstrate the first high-quality radiance field generation results for human bodies. Moreover, we show that our deformation-aware training procedure significantly improves the quality of generated bodies or faces when editing their poses or facial expressions compared to a 3D GAN that is not trained with explicit deformations.

Understanding and modeling the dynamics of human gaze behavior in 360° environments is crucial for creating, improving, and developing emerging virtual reality applications. However, recruiting human observers and acquiring enough data to analyze their behavior when exploring virtual environments requires complex hardware and software setups, and can be time-consuming. Being able to generate virtual observers can help overcome this limitation, and thus stands as an open problem in this medium. Particularly, generative adversarial approaches could alleviate this challenge by generating a large number of scanpaths that reproduce human behavior when observing new scenes, essentially mimicking virtual observers. However, existing methods for scanpath generation do not adequately predict realistic scanpaths for 360° images. We present ScanGAN360, a new generative adversarial approach to address this problem. We propose a novel loss function based on dynamic time warping and tailor our network to the specifics of 360° images. The quality of our generated scanpaths outperforms competing approaches by a large margin, and is almost on par with the human baseline. ScanGAN360 allows fast simulation of large numbers of virtual observers, whose behavior mimics real users, enabling a better understanding of gaze behavior, facilitating experimentation, and aiding novel applications in virtual reality and beyond.

Novel view synthesis is a long-standing problem in machine learning and computer vision. Significant progress has recently been made in developing neural scene representations and rendering techniques that synthesize photorealistic images from arbitrary views. These representations, however, are extremely slow to train and often also slow to render. Inspired by neural variants of image-based rendering, we develop a new neural rendering approach with the goal of quickly learning a high-quality representation which can also be rendered in real-time. Our approach, MetaNLR++, accomplishes this by using a unique combination of a neural shape representation and 2D CNN-based image feature extraction, aggregation, and re-projection. To push representation convergence times down to minutes, we leverage meta learning to learn neural shape and image feature priors which accelerate training. The optimized shape and image features can then be extracted using traditional graphics techniques and rendered in real time. We show that MetaNLR++ achieves similar or better novel view synthesis results in a fraction of the time that competing methods require.

Current LiDAR systems are limited in their ability to capture dense 3D point clouds. To overcome this challenge, deep learning-based depth completion algorithms have been developed to inpaint missing depth guided by an RGB image. However, these methods fail for low sampling rates. Here, we propose an adaptive sampling scheme for LiDAR systems that demonstrates state-of-the-art performance for depth completion at low sampling rates. Our system is fully differentiable, allowing the sparse depth sampling and the depth inpainting components to be trained end-to-end with an upstream task.

Implicitly defined, continuous, differentiable signal representations parameterized by neural networks have emerged as a powerful paradigm, offering many possible benefits over conventional representations. However, current network architectures for such implicit neural representations are incapable of modeling signals with fine detail, and fail to represent a signal's spatial and temporal derivatives, despite the fact that these are essential to many physical signals defined implicitly as the solution to partial differential equations. We propose to leverage periodic activation functions for implicit neural representations and demonstrate that these networks, dubbed sinusoidal representation networks or SIRENs, are ideally suited for representing complex natural signals and their derivatives. We analyze SIREN activation statistics to propose a principled initialization scheme and demonstrate the representation of images, wavefields, video, sound, and their derivatives. Further, we show how SIRENs can be leveraged to solve challenging boundary value problems, such as particular Eikonal equations (yielding signed distance functions), the Poisson equation, and the Helmholtz and wave equations. Lastly, we combine SIRENs with hypernetworks to learn priors over the space of SIREN functions.

Shaping codes are used to encode information for use on channels with cost constraints. Applications include data transmission with a power constraint and, more recently, data storage on flash memories with a constraint on memory cell wear. In the latter application, system requirements often impose a rate constraint. In this paper, we study rate-constrained fixed-to-variable length shaping codes for noiseless, memoryless costly channels and general i.i.d. sources. The analysis relies on the theory of word-valued sources. We establish a relationship between the code expansion factor - the ratio of the expected codeword length to the length of the input source word - and the minimum average symbol cost. We then determine the expansion factor that minimizes the average cost per source symbol (total cost), corresponding to a conventional optimal source code with cost. An equivalence is established between codes minimizing average symbol cost and codes minimizing total cost, and a separation theorem is proved, showing that optimal shaping can be achieved by a concatenation of optimal compression and optimal shaping for a uniform i.i.d. source. Shaping codes often incorporate, either explicitly or implicitly, some form of non-equiprobable signaling. We use our results to further explore the connections between shaping codes and codes that map a sequence of i.i.d. source symbols into an output sequence of symbols that are approximately independent and distributed according to a specified target distribution, such as distribution matching (DM) codes. Optimal DM codes are characterized in terms of a new performance measure - generalized expansion factor (GEF) - motivated by the costly channel perspective. The GEF is used to study DM codes that minimize informational divergence and normalized informational divergence.