Search

Neural Radiance Fields (NeRFs) have revolutionized scene novel view synthesis, offering visually realistic, precise, and robust implicit reconstructions. While recent approaches enable NeRF editing, such as object removal, 3D shape modification, or material property manipulation, the manual annotation prior to such edits makes the process tedious. Additionally, traditional 2D interaction tools lack an accurate sense of 3D space, preventing precise manipulation and editing of scenes. In this paper, we introduce a novel approach, called Blueprint Neural Field (BluNF), to address these editing issues. BluNF provides a robust and user-friendly 2D blueprint, enabling intuitive scene editing. By leveraging implicit neural representation, BluNF constructs a blueprint of a scene using prior semantic and depth information. The generated blueprint allows effortless editing and manipulation of NeRF representations. We demonstrate BluNF's editability through an intuitive click-and-change mechanism, enabling 3D manipulations, such as masking, appearance modification, and object removal. Our approach significantly contributes to visual content creation, paving the way for further research in this area., Comment: ICCV-W (AI3DCC) 2023. Project page with videos and code: https://www.lix.polytechnique.fr/vista/projects/2023_iccvw_courant/

An audiobook can dramatically improve a work of literature's accessibility and improve reader engagement. However, audiobooks can take hundreds of hours of human effort to create, edit, and publish. In this work, we present a system that can automatically generate high-quality audiobooks from online e-books. In particular, we leverage recent advances in neural text-to-speech to create and release thousands of human-quality, open-license audiobooks from the Project Gutenberg e-book collection. Our method can identify the proper subset of e-book content to read for a wide collection of diversely structured books and can operate on hundreds of books in parallel. Our system allows users to customize an audiobook's speaking speed and style, emotional intonation, and can even match a desired voice using a small amount of sample audio. This work contributed over five thousand open-license audiobooks and an interactive demo that allows users to quickly create their own customized audiobooks. To listen to the audiobook collection visit \url{https://aka.ms/audiobook}.

In this paper, we present MuLanTTS, the Microsoft end-to-end neural text-to-speech (TTS) system designed for the Blizzard Challenge 2023. About 50 hours of audiobook corpus for French TTS as hub task and another 2 hours of speaker adaptation as spoke task are released to build synthesized voices for different test purposes including sentences, paragraphs, homographs, lists, etc. Building upon DelightfulTTS, we adopt contextual and emotion encoders to adapt the audiobook data to enrich beyond sentences for long-form prosody and dialogue expressiveness. Regarding the recording quality, we also apply denoise algorithms and long audio processing for both corpora. For the hub task, only the 50-hour single speaker data is used for building the TTS system, while for the spoke task, a multi-speaker source model is used for target speaker fine tuning. MuLanTTS achieves mean scores of quality assessment 4.3 and 4.5 in the respective tasks, statistically comparable with natural speech while keeping good similarity according to similarity assessment. The excellent and similarity in this year's new and dense statistical evaluation show the effectiveness of our proposed system in both tasks., Comment: 6 pages

Face-to-face communication is a common scenario including roles of speakers and listeners. Most existing research methods focus on producing speaker videos, while the generation of listener heads remains largely overlooked. Responsive listening head generation is an important task that aims to model face-to-face communication scenarios by generating a listener head video given a speaker video and a listener head image. An ideal generated responsive listening video should respond to the speaker with attitude or viewpoint expressing while maintaining diversity in interaction patterns and accuracy in listener identity information. To achieve this goal, we propose the \textbf{M}ulti-\textbf{F}aceted \textbf{R}esponsive Listening Head Generation Network (MFR-Net). Specifically, MFR-Net employs the probabilistic denoising diffusion model to predict diverse head pose and expression features. In order to perform multi-faceted response to the speaker video, while maintaining accurate listener identity preservation, we design the Feature Aggregation Module to boost listener identity features and fuse them with other speaker-related features. Finally, a renderer finetuned with identity consistency loss produces the final listening head videos. Our extensive experiments demonstrate that MFR-Net not only achieves multi-faceted responses in diversity and speaker identity information but also in attitude and viewpoint expression., Comment: Accepted by ACM MM 2023

In this paper, we consider Riemannian online convex optimization with dynamic regret. First, we propose two novel algorithms, namely the Riemannian Online Optimistic Gradient Descent (R-OOGD) and the Riemannian Adaptive Online Optimistic Gradient Descent (R-AOOGD), which combine the advantages of classical optimistic algorithms with the rich geometric properties of Riemannian manifolds. We analyze the dynamic regrets of the R-OOGD and R-AOOGD in terms of regularity of the sequence of cost functions and comparators. Next, we apply the R-OOGD to Riemannian zero-sum games, leading to the Riemannian Optimistic Gradient Descent Ascent algorithm (R-OGDA). We analyze the average iterate and best-iterate of the R-OGDA in seeking Nash equilibrium for a two-player, zero-sum, g-convex-concave games. We also prove the last-iterate convergence of the R-OGDA for g-strongly convex-strongly concave problems. Our theoretical analysis shows that all proposed algorithms achieve results in regret and convergence that match their counterparts in Euclidean spaces. Finally, we conduct several experiments to verify our theoretical findings.

A major challenge in the development of quantum technologies is to induce additional types of ferroic orders into materials that exhibit other useful quantum properties. Various techniques have been applied to this end, such as elastically straining, doping, or interfacing a compound with other materials. Plastic deformation introduces permanent topological defects and large local strains into a material, which can give rise to qualitatively new functionality. Here we show via local magnetic imaging that plastic deformation induces robust magnetism in the quantum paraelectric SrTiO3, in both conducting and insulating samples. Our analysis indicates that the magnetic order is localized along dislocation walls and coexists with polar order along the walls. The magnetic signals can be switched on and off in a controllable manner with external stress, which demonstrates that plastically deformed SrTiO3 is a quantum multiferroic. These results establish plastic deformation as a versatile platform for quantum materials engineering.

Low-rank adaptation (LoRA) has emerged as a new paradigm for cost-efficient fine-tuning of large language models (LLMs). However, fine-tuned LLMs often become overconfident especially when fine-tuned on small datasets. Bayesian methods, with their inherent ability to estimate uncertainty, serve as potent tools to mitigate overconfidence and enhance calibration. In this work, we introduce Laplace-LoRA, which applies a Bayesian approach to the LoRA parameters. Specifically, Laplace-LoRA applies a Laplace approximation to the posterior over the LoRA parameters, considerably improving the calibration of fine-tuned LLMs.

Two-dimensional moir\'e materials have emerged as the most versatile platforms for realizing quantum phases of electrons. Here, we explore the stability origins of correlated states in WSe2/WS2 moir\'e superlattices. We find that ultrafast electronic excitation leads to melting of the Mott states on time scales five times longer than predictions from the charge hopping integrals and the melting rates are thermally activated, with activation energies of 18 and 13 meV for the one- and two-hole Mott states, respectively, suggesting significant electron-phonon coupling. DFT calculation of the one-hole Mott state confirms polaron formation and yields a hole-polaron binding energy of 16 meV. These findings reveal a close interplay of electron-electron and electron-phonon interactions in stabilizing the polaronic Mott insulators at transition metal dichalcogenide moir\'e interfaces., Comment: 14 pages, 4 figures, 11 SI figures

As AI-generated content (AIGC) thrives, deepfakes have expanded from single-modality falsification to cross-modal fake content creation, where either audio or visual components can be manipulated. While using two unimodal detectors can detect audio-visual deepfakes, cross-modal forgery clues could be overlooked. Existing multimodal deepfake detection methods typically establish correspondence between the audio and visual modalities for binary real/fake classification, and require the co-occurrence of both modalities. However, in real-world multi-modal applications, missing modality scenarios may occur where either modality is unavailable. In such cases, audio-visual detection methods are less practical than two independent unimodal methods. Consequently, the detector can not always obtain the number or type of manipulated modalities beforehand, necessitating a fake-modality-agnostic audio-visual detector. In this work, we introduce a comprehensive framework that is agnostic to fake modalities, which facilitates the identification of multimodal deepfakes and handles situations with missing modalities, regardless of the manipulations embedded in audio, video, or even cross-modal forms. To enhance the modeling of cross-modal forgery clues, we employ audio-visual speech recognition (AVSR) as a preliminary task. This efficiently extracts speech correlations across modalities, a feature challenging for deepfakes to replicate. Additionally, we propose a dual-label detection approach that follows the structure of AVSR to support the independent detection of each modality. Extensive experiments on three audio-visual datasets show that our scheme outperforms state-of-the-art detection methods with promising performance on modality-agnostic audio/video deepfakes., Comment: This work has been submitted to the IEEE for possible publication

We construct novel scalarized black hole (BH) solutions beyond the general relativity (GR) framework. These scalarized BH solutions are extended from the Schwarzschild one and the non-Schwarzschild one in the pure Einstein-Weyl gravity. By studying the BH entropy and free energy, we demonstrate that the scalarized BH extending from the Schwarzschild one exhibits thermodynamically preferred. We obtain these novel solutions by directly solving the full fourth-order equations of motion. This narrows the problematic solution space obtained by commonly adopted second-order reduction to physically valid spaces. Our findings also unveil the evasion of the no-hair theorem within the realm of higher-derivative gravity., Comment: 7 pages, 8 gigures

The introduction of robots is widely considered to have significant potential of alleviating the issues of worker shortage and stagnant productivity that afflict the construction industry. However, it is challenging to use fully automated robots in complex and unstructured construction sites. Human-Robot Collaboration (HRC) has shown promise of combining human workers' flexibility and robot assistants' physical abilities to jointly address the uncertainties inherent in construction work. When introducing HRC in construction, it is critical to recognize the importance of teamwork and supervision in field construction and establish a natural and intuitive communication system for the human workers and robotic assistants. Natural language-based interaction can enable intuitive and familiar communication with robots for human workers who are non-experts in robot programming. However, limited research has been conducted on this topic in construction. This paper proposes a framework to allow human workers to interact with construction robots based on natural language instructions. The proposed method consists of three stages: Natural Language Understanding (NLU), Information Mapping (IM), and Robot Control (RC). Natural language instructions are input to a language model to predict a tag for each word in the NLU module. The IM module uses the result of the NLU module and building component information to generate the final instructional output essential for a robot to acknowledge and perform the construction task. A case study for drywall installation is conducted to evaluate the proposed approach. The obtained results highlight the potential of using natural language-based interaction to replicate the communication that occurs between human workers within the context of human-robot teams.

While state-of-the-art Text-to-Speech systems can generate natural speech of very high quality at sentence level, they still meet great challenges in speech generation for paragraph / long-form reading. Such deficiencies are due to i) ignorance of cross-sentence contextual information, and ii) high computation and memory cost for long-form synthesis. To address these issues, this work develops a lightweight yet effective TTS system, ContextSpeech. Specifically, we first design a memory-cached recurrence mechanism to incorporate global text and speech context into sentence encoding. Then we construct hierarchically-structured textual semantics to broaden the scope for global context enhancement. Additionally, we integrate linearized self-attention to improve model efficiency. Experiments show that ContextSpeech significantly improves the voice quality and prosody expressiveness in paragraph reading with competitive model efficiency. Audio samples are available at: https://contextspeech.github.io/demo/, Comment: 5 pages, 4 figures, Proceedings of Interspeech 2023