arXiv subjects

Dechao Meng

Publications and source records attributed to Dechao Meng.

14 recordsLinked to original sources

arXiv2026

Wan-Animate-2: Pushing the Application Boundaries of Character Animation

Character image animation remains a foundational yet challenging task in computer vision. Existing approaches can be broadly categorized into three paradigms: methods based on explicit motion representations suffer from extraction errors and identity drift; methods based on implicit motion features lose fine-grained dynamics through compression; and in-context learning approaches avoid intermediate representations but incur prohibitive computational costs. Furthermore, all current systems are designed for offline synthesis, unable to meet the real-time requirements of interactive applications such as digital avatars and live-streaming hosts. To address these limitations, we present Wan-Animate-2, an end-to-end character animation framework that directly consumes the driving video within a redesigned Diffusion Transformer. Our architecture achieves superior motion fidelity and identity preservation by eliminating intermediate motion extractors entirely. We further introduce text driven viewpoint control that decouples the output camera perspective from the driving video--a capability rarely supported by prior character animation methods that rely on explicit motion representations. Beyond generation quality, we present Wan-Animate-2-Lite, an efficient variant that reduces inference latency to real-time thresholds through a three-stage training paradigm: teacher forcing pretraining with error buffer mechanism, and Self-Forcing distillation with chunk-wise backpropagation. This enables streaming character animation for interactive applications, opening new deployment scenarios that were previously infeasible. Qualitative evaluations and user studies demonstrate that Wan-Animate-2 achieves high-fidelity animation results across diverse characters and motion patterns. To foster further research and community development, we will release the Wan-Animate-2-Base model weights to the public.

cs.CV↗

arXiv2025

Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation

Real-time portrait animation is essential for interactive applications such as virtual assistants and live avatars, requiring high visual fidelity, temporal coherence, ultra-low latency, and responsive control from dynamic inputs like reference images and driving signals. While diffusion-based models achieve strong quality, their non-causal nature hinders streaming deployment. Causal autoregressive video generation approaches enable efficient frame-by-frame generation but suffer from error accumulation, motion discontinuities at chunk boundaries, and degraded long-term consistency. In this work, we present a novel streaming framework named Knot Forcing for real-time portrait animation that addresses these challenges through three key designs: (1) a chunk-wise generation strategy with global identity preservation via cached KV states of the reference image and local temporal modeling using sliding window attention; (2) a temporal knot module that overlaps adjacent chunks and propagates spatio-temporal cues via image-to-video conditioning to smooth inter-chunk motion transitions; and (3) A "running ahead" mechanism that dynamically updates the reference frame's temporal coordinate during inference, keeping its semantic context ahead of the current rollout frame to support long-term coherence. Knot Forcing enables high-fidelity, temporally consistent, and interactive portrait animation over infinite sequences, achieving real-time performance with strong visual stability on consumer-grade GPUs.

cs.CV↗

arXiv2025

SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild

High-quality AI-powered video dubbing demands precise audio-lip synchronization, high-fidelity visual generation, and faithful preservation of identity and background. Most existing methods rely on a mask-based training strategy, where the mouth region is masked in talking-head videos, and the model learns to synthesize lip movements from corrupted inputs and target audios. While this facilitates lip-sync accuracy, it disrupts spatiotemporal context, impairing performance on dynamic facial motions and causing instability in facial structure and background consistency. To overcome this limitation, we propose SyncAnyone, a novel two-stage learning framework that achieves accurate motion modeling and high visual fidelity simultaneously. In Stage 1, we train a diffusion-based video transformer for masked mouth inpainting, leveraging its strong spatiotemporal modeling to generate accurate, audio-driven lip movements. However, due to input corruption, minor artifacts may arise in the surrounding facial regions and the background. In Stage 2, we develop a mask-free tuning pipeline to address mask-induced artifacts. Specifically, on the basis of the Stage 1 model, we develop a data generation pipeline that creates pseudo-paired training samples by synthesizing lip-synced videos from the source video and random sampled audio. We further tune the stage 2 model on this synthetic data, achieving precise lip editing and better background consistency. Extensive experiments show that our method achieves state-of-the-art results in visual quality, temporal coherence, and identity preservation under in-the wild lip-syncing scenarios.

cs.CV↗

arXiv2025

Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

We introduce Wan-Animate, a unified framework for character animation and replacement. Given a character image and a reference video, Wan-Animate can animate the character by precisely replicating the expressions and movements of the character in the video to generate high-fidelity character videos. Alternatively, it can integrate the animated character into the reference video to replace the original character, replicating the scene's lighting and color tone to achieve seamless environmental integration. Wan-Animate is built upon the Wan model. To adapt it for character animation tasks, we employ a modified input paradigm to differentiate between reference conditions and regions for generation. This design unifies multiple tasks into a common symbolic representation. We use spatially-aligned skeleton signals to replicate body motion and implicit facial features extracted from source images to reenact expressions, enabling the generation of character videos with high controllability and expressiveness. Furthermore, to enhance environmental integration during character replacement, we develop an auxiliary Relighting LoRA. This module preserves the character's appearance consistency while applying the appropriate environmental lighting and color tone. Experimental results demonstrate that Wan-Animate achieves state-of-the-art performance. We are committed to open-sourcing the model weights and its source code.

cs.CV↗

arXiv2025

Wan-S2V: Audio-Driven Cinematic Video Generation

Current state-of-the-art (SOTA) methods for audio-driven character animation demonstrate promising performance for scenarios primarily involving speech and singing. However, they often fall short in more complex film and television productions, which demand sophisticated elements such as nuanced character interactions, realistic body movements, and dynamic camera work. To address this long-standing challenge of achieving film-level character animation, we propose an audio-driven model, which we refere to as Wan-S2V, built upon Wan. Our model achieves significantly enhanced expressiveness and fidelity in cinematic contexts compared to existing approaches. We conducted extensive experiments, benchmarking our method against cutting-edge models such as Hunyuan-Avatar and Omnihuman. The experimental results consistently demonstrate that our approach significantly outperforms these existing solutions. Additionally, we explore the versatility of our method through its applications in long-form video generation and precise video lip-sync editing.

cs.CV↗

arXiv2025

MirrorMe: Towards Realtime and High Fidelity Audio-Driven Halfbody Animation

Audio-driven portrait animation, which synthesizes realistic videos from reference images using audio signals, faces significant challenges in real-time generation of high-fidelity, temporally coherent animations. While recent diffusion-based methods improve generation quality by integrating audio into denoising processes, their reliance on frame-by-frame UNet architectures introduces prohibitive latency and struggles with temporal consistency. This paper introduces MirrorMe, a real-time, controllable framework built on the LTX video model, a diffusion transformer that compresses video spatially and temporally for efficient latent space denoising. To address LTX's trade-offs between compression and semantic fidelity, we propose three innovations: 1. A reference identity injection mechanism via VAE-encoded image concatenation and self-attention, ensuring identity consistency; 2. A causal audio encoder and adapter tailored to LTX's temporal structure, enabling precise audio-expression synchronization; and 3. A progressive training strategy combining close-up facial training, half-body synthesis with facial masking, and hand pose integration for enhanced gesture control. Extensive experiments on the EMTD Benchmark demonstrate MirrorMe's state-of-the-art performance in fidelity, lip-sync accuracy, and temporal stability.

cs.CV↗

arXiv2025

Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance

Recent character image animation methods based on diffusion models, such as Animate Anyone, have made significant progress in generating consistent and generalizable character animations. However, these approaches fail to produce reasonable associations between characters and their environments. To address this limitation, we introduce Animate Anyone 2, aiming to animate characters with environment affordance. Beyond extracting motion signals from source video, we additionally capture environmental representations as conditional inputs. The environment is formulated as the region with the exclusion of characters and our model generates characters to populate these regions while maintaining coherence with the environmental context. We propose a shape-agnostic mask strategy that more effectively characterizes the relationship between character and environment. Furthermore, to enhance the fidelity of object interactions, we leverage an object guider to extract features of interacting objects and employ spatial blending for feature injection. We also introduce a pose modulation strategy that enables the model to handle more diverse motion patterns. Experimental results demonstrate the superior performance of the proposed method.

cs.CV↗

arXiv2022

Surface engineering for ultrathin metal anodes enabling high-performance Zn-ion batteries

Zn metal battery has been considered a promising alternative energy storage technology in renewable energy storage and grid storage. It is well-known that the surface orientation of a Zn metal anode is vital to the reversibility of a Zn metal battery. Herein, the (101)-oriented thin Zn metal anode (down to 2 {\mu}m) is electrodeposited on a Cu surface by adding dimethyl sulfoxide (DMSO) electrolyte additive in ZnSO4 aqueous solution. Scanning electron microscope (SEM) observation indicates the formation of flat terrace-like compact (101)-oriented surfaces. Insitu optical observation confirms that the (101)-oriented surfaces can be reversibly plated and stripped. DFT calculations reveal two mechanisms for the nucleation and growth of the Zn-(101) surface: (1) formation of Zn(101)//Cu(001) could lower the interface energy as compared to Zn(002)//Cu(001); (2) large reconstruction of the Zn (101) surface with DMSO and H2O absorption. Raman, XPS, and ToF-SIMS characterizations indicate that adding DMSO in ZnCl2 could facilitate the formation of ZnO-based SEI on Zn metal surface, while OH- and S-based SEI can be obtained with DMSO in ZnSO4. The electrochemical testings are performed, which demonstrates a higher cyclability for the (101)-oriented Zn in the half cell as well as a lower charge transfer barrier with respect to the (002)-dominated surface of the same electrode thickness. Zn||V2O5 full cells are further assembled, showing better capacity retention for the (101)-Zn as compared to the (002)-Zn with the same thickness (5 {\mu}m, 3 {\mu}m, and 2 {\mu}m). We hope this study to spur further interest in the control of Zn metal surface crystallographic orientation towards ultrathin Zn metal anodes.

cond-mat.mtrl-sci↗

arXiv2021

Emerging Oscillating Reactions at the Insulator/Semiconductor Solid/Solid Interface via Proton Implantation

Most oscillating reactions (ORs) happen in solutions. Few existing solid-based ORs either happen on solid/gas (e.g., oxidation or corrosion) or solid/liquid interfaces, or at the all-solid interfaces neighboring to metals or ionic conductors (e.g., electrolysis or electroplate). We report in this paper a new type of all-solid based OR that happens at the insulator (amorphous SiO$_2$)/semiconductor (Si) interface with the interfacial point defects as the oscillating species. This OR is the first example of the point-defect coupled ORs (PDC-ORs) proposed by H. Schmalzried et al. and J. Janek et al. decades ago. We use proton implantation as the driving force of the oscillation, and employ techniques common in semiconductor device characterization to monitor the oscillation in situ. This approach not only overcomes the difficulties associated with detecting reactions in solids, but also accurately measure the oscillating ultra-low concentration ($10^{10}\sim10^{11}$ cm$^{-2}$) of the interfacial charged point-defects. We propose a mechanism for the reported PDC-OR based on the Brusselator model by identifying the interfacial reactions.

physics.chem-ph↗

arXiv2020

Parsing-based View-aware Embedding Network for Vehicle Re-Identification

Vehicle Re-Identification is to find images of the same vehicle from various views in the cross-camera scenario. The main challenges of this task are the large intra-instance distance caused by different views and the subtle inter-instance discrepancy caused by similar vehicles. In this paper, we propose a parsing-based view-aware embedding network (PVEN) to achieve the view-aware feature alignment and enhancement for vehicle ReID. First, we introduce a parsing network to parse a vehicle into four different views, and then align the features by mask average pooling. Such alignment provides a fine-grained representation of the vehicle. Second, in order to enhance the view-aware features, we design a common-visible attention to focus on the common visible views, which not only shortens the distance among intra-instances, but also enlarges the discrepancy of inter-instances. The PVEN helps capture the stable discriminative information of vehicle under different views. The experiments conducted on three datasets show that our model outperforms state-of-the-art methods by a large margin.

cs.CV↗

arXiv2019

Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding

Weakly supervised referring expression grounding aims at localizing the referential object in an image according to the linguistic query, where the mapping between the referential object and query is unknown in the training stage. To address this problem, we propose a novel end-to-end adaptive reconstruction network (ARN). It builds the correspondence between image region proposal and query in an adaptive manner: adaptive grounding and collaborative reconstruction. Specifically, we first extract the subject, location and context features to represent the proposals and the query respectively. Then, we design the adaptive grounding module to compute the matching score between each proposal and query by a hierarchical attention model. Finally, based on attention score and proposal features, we reconstruct the input query with a collaborative loss of language reconstruction loss, adaptive reconstruction loss, and attribute classification loss. This adaptive mechanism helps our model to alleviate the variance of different referring expressions. Experiments on four large-scale datasets show ARN outperforms existing state-of-the-art methods by a large margin. Qualitative results demonstrate that the proposed ARN can better handle the situation where multiple objects of a particular category situated together.

cs.CV↗

arXiv2019

Direct Imaging Revealing Halved Ferromagnetism in Tensile-Strained LaCoO3 Thin Films

The enigma of the emergent ferromagnetic state in tensile-strained LaCoO3 thin films remains to be explored because of the lack of a well agreed explanation. The direct magnetic imaging technique using a low-temperature magnetic force microscope (MFM) is critical to reveal new aspects of the ferromagnetism by investigating the lateral magnetic phase distribution. Here we show the experimental demonstration of the rare halved occupation of the ferromagnetic state in tensile-strained LaCoO3 thin films on SrTiO3 substrates using the MFM. The films have uniformly strained lattice structure and minimal oxygen vacancies (less than 2%) beyond the measurement limit. It is found that percolated ferromagnetic regions with typical sizes between 100 nm and 200 nm occupy about 50% of the entire film, even down to the lowest achievable temperature of 4.5 K and up to the largest magnetic field of 13.4 T. Preformed ferromagnetic droplets were still observed when the temperature is 20 K above the Curie temperature indicating the existence of possible Griffiths phase. Our study demonstrated a sub-micron level phase separation in high quality LaCoO3 thin films, which has substantial implications in revealing the intrinsic nature of the emergent ferromagnetism.

cond-mat.str-el↗

arXiv2019

Linear Dependence of Post-irradiation Input Bias Currents on Pre-irradiation Values in Silicon Bipolar Microcircuits

We find in experiments a linear dependence of ionization irradiation-induced degradations on pre-irradiation values of the input bias current in bipolar devices with simple input stages. The dependence is found to generally exist in all studied cases of different device types and different irradiation conditions. A unique behavior of the energy distribution of the interface states ($D_{it}$) under irradiation is suggested as the origin of the observed phenomenon: the generation of interface traps through the depassivation of Si-H bonds located near the pre-irradiation interface traps displays a $D_{it}$ as an enlarge of the initial $D_{it}$ and results in the general linear dependence. A more accurate damage prediction method by using the pre-irradiation values is proposed based on the observed phenomenon.

physics.space-ph↗

arXiv2019

Mechanism of Synergistic Effects of Neutron- and Gamma-Ray-Radiated PNP Bipolar Transistors

The synergistic effects of neutron and gamma ray radiated PNP transistors are systematically investigated as functions of the neutron fluence, gamma ray dose, and dose rate. We find that the damages show a `tick'-like dependence on the gamma ray dose after the samples are radiated by neutrons. Two negative synergistic effects are derived, both of which have similar magnitudes as the ionization damage (ID) itself. The first one depends linearly on the gamma ray dose, whose slope depends quadratically on the initial displacement damage (DD) and can be attributed to the healing of neutron-radiation-induced defects in silicon. The second one has an exponential decay with the gamma ray dose, whose amplitude shows a rather strong enhanced low-dose-rate sensitivity (ELDRS) effect and can be attributed to the passivation of neutron-induced defects near the silica/silicon interface by the gamma-ray-generated protons in silica, which can penetrate the silica/silicon interface to passivate the neutron-induced defects in silicon. The simulated results based on the proposed model match the experimental data very well, but differ from previous model, which does not assume annihilation or passivation of the displacement defects. The unraveled defect annealing mechanism is important because it implies that displacement damages can be repaired by gamma ray radiation or proton diffusion, which can have important device applications in the space or other extreme environments.

physics.app-ph↗