NeurIPS 2023 Papers

Neural radiance fields (NeRFs) are able to synthesize realistic novel views from multi-view images captured from distinct positions and perspectives. In NeRF's rendering pipeline, neural networks are used to represent a scene independently or transform queried learnable feature vector of a point to the expected color or density. With the aid of geometry guides either in the form of occupancy grids or proposal networks, the number of color neural network evaluations can be reduced from hundreds to dozens in the standard volume rendering framework. However, many evaluations of the color neural network are still a bottleneck for fast NeRF reconstruction. This paper revisits volume feature rendering (VFR) for the purpose of fast NeRF reconstruction. The VFR integrates the queried feature vectors of a ray into one feature vector, which is then transformed to the final pixel color by a color neural network. This fundamental change to the standard volume rendering framework requires only one single color neural network evaluation to render a pixel, which substantially lowers the high computational complexity of the rendering framework attributed to a large number of color neural network evaluations. Consequently, we can use a comparably larger color neural network to achieve a better rendering quality while maintaining the same training and rendering time costs. This approach achieves the state-of-the-art rendering quality on both synthetic and real-world datasets while requiring less training time compared with existing methods.

Generalizable neural surface reconstruction techniques have attracted great attention in recent years. However, they encounter limitations of low confidence depth distribution and inaccurate surface reasoning due to the oversimplified volume rendering process employed. In this paper, we present Reconstruction TRansformer (ReTR), a novel framework that leverages the transformer architecture to redesign the rendering process, enabling complex render interaction modeling. It introduces a learnable $\textit{meta-ray token}$ and utilizes the cross-attention mechanism to simulate the interaction of rendering process with sampled points and render the observed color. Meanwhile, by operating within a high-dimensional feature space rather than the color space, ReTR mitigates sensitivity to projected colors in source views. Such improvements result in accurate surface assessment with high confidence. We demonstrate the effectiveness of our approach on various datasets, showcasing how our method outperforms the current state-of-the-art approaches in terms of reconstruction quality and generalization ability. $\textit{Our code is available at }$ https://github.com/YixunLiang/ReTR.

The bird's-eye-view (BEV) perception plays a critical role in autonomous driving systems, involving the accurate and efficient detection and tracking of objects from a top-down perspective. To achieve real-time decision-making in self-driving scenarios, low-latency computation is essential. While recent approaches to BEV detection have focused on improving detection precision using Lift-Splat-Shoot (LSS)-based or transformer-based schemas, the substantial computational and memory burden of these approaches increases the risk of system crashes when multiple on-vehicle tasks run simultaneously. Unfortunately, there is a dearth of literature on efficient BEV detector paradigms, let alone achieving realistic speedups. Unlike existing works that focus on reducing computation costs, this paper focuses on developing an efficient model design that prioritizes actual on-device latency. To achieve this goal, we propose a latency-aware design methodology that considers key hardware properties, such as memory access cost and degree of parallelism. Given the prevalence of GPUs as the main computation platform for autonomous driving systems, we develop a theoretical latency prediction model and introduce efficient building operators. By leveraging these operators and following an effective local-to-global visual modeling process, we propose a hardware-oriented backbone that is also optimized for strong feature capturing and fusing. Using these insights, we present a new hardware-oriented framework for efficient yet accurate camera-view BEV detectors. Experiments show that HotBEV achieves a 2\%$\sim$23\% NDS gain, and 2\%$\sim$7.8\% mAP gain with a 1.1$\times$$\sim$3.4$\times$ speedups compared to existing works on V100; On multiple GPU devices such as GPU GTX 2080 and the low-end GTX 1080, HotBEV achieves 1.1$\times$$\sim$6.3$\times$ faster than others.

Steerable convolutional neural networks (CNNs) provide a general framework for building neural networks equivariant to translations and transformations of an origin-preserving group $G$, such as reflections and rotations. They rely on standard convolutions with $G$-steerable kernels obtained by analytically solving the group-specific equivariance constraint imposed onto the kernel space. As the solution is tailored to a particular group $G$, implementing a kernel basis does not generalize to other symmetry transformations, complicating the development of general group equivariant models. We propose using implicit neural representation via multi-layer perceptrons (MLPs) to parameterize $G$-steerable kernels. The resulting framework offers a simple and flexible way to implement Steerable CNNs and generalizes to any group $G$ for which a $G$-equivariant MLP can be built. We prove the effectiveness of our method on multiple tasks, including N-body simulations, point cloud classification and molecular property prediction.

Recently, the Segment Anything Model (SAM) emerged as a powerful vision foundation model which is capable to segment anything in 2D images. This paper aims to generalize SAM to segment 3D objects. Rather than replicating the data acquisition and annotation procedure which is costly in 3D, we design an efficient solution, leveraging the Neural Radiance Field (NeRF) as a cheap and off-the-shelf prior that connects multi-view 2D images to the 3D space. We refer to the proposed solution as SA3D, for Segment Anything in 3D. It is only required to provide a manual segmentation prompt (e.g., rough points) for the target object in a single view, which is used to generate its 2D mask in this view with SAM. Next, SA3D alternately performs mask inverse rendering and cross-view self-prompting across various views to iteratively complete the 3D mask of the target object constructed with voxel grids. The former projects the 2D mask obtained by SAM in the current view onto 3D mask with guidance of the density distribution learned by the NeRF; The latter extracts reliable prompts automatically as the input to SAM from the NeRF-rendered 2D mask in another view. We show in experiments that SA3D adapts to various scenes and achieves 3D segmentation within minutes. Our research offers a generic and efficient methodology to lift a 2D vision foundation model to 3D, as long as the 2D model can steadily address promptable segmentation across multiple views.

Visual stylization has been a very popular research area in recent times. While image stylization has seen a rapid advancement in the recent past, video stylization, while being more challenging, is relatively less explored. The immediate method of stylizing videos by stylizing each frame independently has been tried with some success. To the best of our knowledge, we present the first approach to video stylization using 3D CNN directly, building upon insights from 2D image stylization. Stylizing video is highly challenging, as the appearance and video motion, which includes both camera and subject motions, are inherently entangled in the representations learnt by a 3D CNN. Hence, a naive extension of 2D CNN stylization methods to 3D CNN does not work. To perform stylization with 3D CNN, we propose to explicitly disentangle motion and appearance, stylize the appearance part, and then add back the motion component and decode the final stylized video. In addition, we propose a dataset, curated from existing datasets, to train video stylization networks. We also provide an independently collected test set to study the generalization of video stylization methods. We provide results on this test dataset comparing the proposed method with 2D stylization methods applied frame by frame. We show successful stylization with 3D CNN for the first time, and obtain better stylization in terms of texture cf.\ the existing 2D methods.

Synthesizing high-fidelity head avatars is a central problem for computer vision and graphics. While head avatar synthesis algorithms have advanced rapidly, the best ones still face great obstacles in real-world scenarios. One of the vital causes is the inadequate datasets -- 1) current public datasets can only support researchers to explore high-fidelity head avatars in one or two task directions; 2) these datasets usually contain digital head assets with limited data volume, and narrow distribution over different attributes, such as expressions, ages, and accessories. In this paper, we present RenderMe-360, a comprehensive 4D human head dataset to drive advance in head avatar algorithms across different scenarios. It contains massive data assets, with 243+ million complete head frames and over 800k video sequences from 500 different identities captured by multi-view cameras at 30 FPS. It is a large-scale digital library for head avatars with three key attributes: 1) High Fidelity: all subjects are captured in 360 degrees via 60 synchronized, high-resolution 2K cameras. 2) High Diversity: The collected subjects vary from different ages, eras, ethnicities, and cultures, providing abundant materials with distinctive styles in appearance and geometry. Moreover, each subject is asked to perform various dynamic motions, such as expressions and head rotations, which further extend the richness of assets. 3) Rich Annotations: the dataset provides annotations with different granularities: cameras' parameters, background matting, scan, 2D/3D facial landmarks, FLAME fitting, and text description. Based on the dataset, we build a comprehensive benchmark for head avatar research, with 16 state-of-the-art methods performed on five main tasks: novel view synthesis, novel expression synthesis, hair rendering, hair editing, and talking head generation. Our experiments uncover the strengths and flaws of state-of-the-art methods. RenderMe-360 opens the door for future exploration in modern head avatars. All of the data, code, and models will be publicly available at https://renderme-360.github.io/.

This paper presents Decorate3D, a versatile and user-friendly method for the creation and editing of 3D objects using images. Decorate3D models a real-world object of interest by neural radiance field (NeRF) and decomposes the NeRF representation into an explicit mesh representation, a view-dependent texture, and a diffuse UV texture. Subsequently, users can either manually edit the UV or provide a prompt for the automatic generation of a new 3D-consistent texture. To achieve high-quality 3D texture generation, we propose a structure-aware score distillation sampling method to optimize a neural UV texture based on user-defined text and empower an image diffusion model with 3D-consistent generation capability. Furthermore, we introduce a few-view resampling training method and utilize a super-resolution model to obtain refined high-resolution UV textures (2048$\times$2048) for 3D texturing. Extensive experiments collectively validate the superior performance of Decorate3D in retexturing real-world 3D objects. Project page: https://decorate3d.github.io/Decorate3D/.

Neural rendering is fuelling a unification of learning, 3D geometry and video understanding that has been waiting for more than two decades. Progress, however, is still hampered by a lack of suitable datasets and benchmarks. To address this gap, we introduce EPIC Fields, an augmentation of EPIC-KITCHENS with 3D camera information. Like other datasets for neural rendering, EPIC Fields removes the complex and expensive step of reconstructing cameras using photogrammetry, and allows researchers to focus on modelling problems. We illustrate the challenge of photogrammetry in egocentric videos of dynamic actions and propose innovations to address them. Compared to other neural rendering datasets, EPIC Fields is better tailored to video understanding because it is paired with labelled action segments and the recent VISOR segment annotations. To further motivate the community, we also evaluate two benchmark tasks in neural rendering and segmenting dynamic objects, with strong baselines that showcase what is not possible today. We also highlight the advantage of geometry in semi-supervised video object segmentations on the VISOR annotations. EPIC Fields reconstructs 96\% of videos in EPIC-KITCHENS, registering 19M frames in 99 hours recorded in 45 kitchens, and is available from: http://epic-kitchens.github.io/epic-fields

Controllable scene synthesis aims to create interactive environments for numerous industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner. Existing methods, reliant on retrieval from extensive databases or pre-trained shape embeddings, often overlook scene-object and object-object relationships, leading to inconsistent results due to their limited generation capacity. To address this issue, we present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes, which are semantically realistic and conform to commonsense. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes via latent diffusion, capturing global scene-object and local inter-object relationships in the scene graph while preserving shape diversity. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model. Due to the lack of a scene graph dataset offering high-quality object-level meshes with relations, we also construct SG-FRONT, enriching the off-the-shelf indoor dataset 3D-FRONT with additional scene graph labels. Extensive experiments are conducted on SG-FRONT, where CommonScenes shows clear advantages over other methods regarding generation consistency, quality, and diversity. Codes and the dataset are available on the website.

Recently, text-guided 3D generative methods have made remarkable advancements in producing high-quality textures and geometry, capitalizing on the proliferation of large vision-language and image diffusion models. However, existing methods still struggle to create high-fidelity 3D head avatars in two aspects: (1) They rely mostly on a pre-trained text-to-image diffusion model whilst missing the necessary 3D awareness and head priors. This makes them prone to inconsistency and geometric distortions in the generated avatars. (2) They fall short in fine-grained editing. This is primarily due to the inherited limitations from the pre-trained 2D image diffusion models, which become more pronounced when it comes to 3D head avatars. In this work, we address these challenges by introducing a versatile coarse-to-fine pipeline dubbed HeadSculpt for crafting (i.e., generating and editing) 3D head avatars from textual prompts. Specifically, we first equip the diffusion model with 3D awareness by leveraging landmark-based control and a learned textual embedding representing the back view appearance of heads, enabling 3D-consistent head avatar generations. We further propose a novel identity-aware editing score distillation strategy to optimize a textured mesh with a high-resolution differentiable rendering technique. This enables identity preservation while following the editing instruction. We showcase HeadSculpt's superior fidelity and editing capabilities through comprehensive experiments and comparisons with existing methods.