Neural Radiance Field (NeRF) has broken new ground in the novel view synthesis due to its simple concept and state-of-the-art quality. However, it suffers from severe performance degradation unless trained with a dense set of images with different camera poses, which hinders its practical applications. Although previous methods addressing this problem achieved promising results, they relied heavily on the additional training resources, which goes against the philosophy of sparse-input novel-view synthesis pursuing the training efficiency. In this work, we propose MixNeRF, an effective training strategy for novel view synthesis from sparse inputs by modeling a ray with a mixture density model. Our MixNeRF estimates the joint distribution of RGB colors along the ray samples by modeling it with mixture of distributions. We also propose a new task of ray depth estimation as a useful training objective, which is highly correlated with 3D scene geometry. Moreover, we remodel the colors with regenerated blending weights based on the estimated ray depth and further improves the robustness for colors and viewpoints. Our MixNeRF outperforms other state-of-the-art methods in various standard benchmarks with superior efficiency of training and inference.
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；National Taiwan University（国立台湾大学）；Massachusetts Institute of Technology（麻省理工学院）
We present Neural Mixtures of Planar Experts (NeurMiPs), a novel planar-based scene representation for modeling geometry and appearance. NeurMiPs leverages a collection of local planar experts in 3D space as the scene representation. Each planar expert consists of the parameters of the local rectangular shape representing geometry and a neural radiance field modeling the color and opacity. We render novel views by calculating ray-plane intersections and composite output colors and densities at intersected points to the image. NeurMiPs blends the efficiency of explicit mesh rendering and flexib…
MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis
South China University of Technology（华南理工大学）；JD Explore Academy（京东探索研究院）；Nanyang Technological University（南洋理工大学）；Shanghai Jiao Tong University（上海交通大学）
Stereo-Talker: Audio-driven 3D Human Synthesis with Prior-Guided Mixture-of-Experts
Department of Automation, Tsinghua University（自动化系，清华大学）；Bytedance Inc.（字节跳动公司）；State Key Laboratory of Media Convergence and Communication, Communication University of China（媒体融合与传播国家重点实验室，中国传媒大学）；School of Artificial Intelligence, Beijing Normal University（人工智能学院，北京师范大学）
Spatio-Temporal Mixture-of-Modality-Experts Diffusion for Quantitative DCE-MRI Synthesis from Incomplete MR Sequences
Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine（首尔大学医学院癌症生物学跨学科项目）；Department of Radiology, Seoul National University Hospital（首尔大学医院放射科）；Department of Radiology, Seoul National University College of Medicine（首尔大学医学院放射科）；Healthcare AI Research Institute, Seoul National University Hospital（首尔大学医院医疗人工智能研究所）
Unified Cross-Modal Medical Image Synthesis with Hierarchical Mixture of Product-of-Experts
Harvard Medical School and the Brigham and Women’s Hospital（哈佛医学院和布里洛妇产科医院）；MIND Team, Inria Saclay, Université Paris-Saclay, Palaiseau, France and Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié Salpêtrière（MIND团队、Inria Saclay、巴黎萨克雷大学、Palaiseau，法国以及索邦大学、巴黎脑研究所-ICM、CNRS、Inria、Inserm、AP-HP、皮蒂埃萨勒普蒂耶医院）；Massachusetts Institute of Technology（麻省理工学院）
University of Bologna（博洛尼亚大学）；Google Inc.（谷歌公司）；Technische Universität München（慕尼黑工业大学）
Novel view synthesis from a single image has recently achieved remarkable results, although the requirement of some form of 3D, pose, or multi-view supervision at training time limits the deployment in real scenarios. This work aims at relaxing these assumptions enabling training of conditional generative models for novel view synthesis in a completely unsupervised manner. We first pre-train a purely generative decoder model using a 3D-aware GAN formulation while at the same time train an encoder network to invert the mapping from latent space to images. Then, we swap encoder and decoder and t…
The generation of synthetic images is currently being dominated by Generative Adversarial Networks (GANs). Despite their outstanding success in generating realistic looking images, they still suffer from major drawbacks, including an unstable and highly sensitive training procedure, mode-collapse and mode-mixture, and dependency on large training sets. In this work we present a novel non-adversarial generative method - Clustered Optimization of LAtent space (COLA), which overcomes some of the limitations of GANs, and outperforms GANs when training data is scarce. In the full data regime, our m…
